19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007
|
|
- Marilynn Garrison
- 5 years ago
- Views:
Transcription
1 19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007 AN HMM BASED INVESTIGATION OF DIFFERENCES BETWEEN MUSICAL INSTRUMENTS OF THE SAME TYPE PACS: z Eichner, Matthias; Wolff, Matthias; Hoffmann, Rüdiger Technische Universität Dresden, Laboratory of Acoustics and Speech Communication, Dresden, Germany; ABSTRACT In this paper we present our research on music instrument classification. In contrast to other contributions in this field we try to identify a certain instrument within a set of instruments of the same type. There exist a number of conceivable applications that could make use of this information. Our goal is to provide a tool to instrument makers that allows to measure the influence of changes in the production process on the sound characteristics of an instrument. For this purpose we trained an HMM based recognizer using solo music pieces played on different instruments of the same type under varying conditions. We performed extensive subjective evaluations to study to what extend differences between instruments are perceivable and compared this with the results of the classification experiments. INTRODUCTION Identification of musical instruments in solo and polyphonic music has been a field of research in the past years. Robust musical instrument recognition offers a variety of applications in the field of music content analysis including automatic annotation of musical signals and retrieval of music from a database for given symbolic description. However, distinction of instruments of the same type, like the identification of a certain violin within a number of violins, has been addressed by a few authors only [1][2][3]. Information about the identity of an instrument could be used in a number of applications like analysis of historical recordings or in investigations of insurance companies. Our motivation for the presented research is to provide a tool for instrument makers that tells whether the sound characteristics of an instrument is influenced by modifications in the production process or not. In other words, how do design features influence the sound characteristic of an instrument? Providing such a tool leads to a number of further questions: (a) Are changes in the sound characteristic perceivable by listeners? (b) Are the judgments consistent within a group of listeners? (c) Do the results of the measurements match the judgments of the listeners? (d) Is there a way to determine the characteristic of an unknown instrument by comparison to reference instruments having known characteristics? We try to find answers to these questions and recorded a database consisting of solo music pieces of four different instrument types. This database serves as basis for the subjective evaluations as well as the automatic classification experiments and will be described in section 2. The experimental setup of the subjective evaluations and knowledge gained from those experiments will be presented in section 3. In section 4 we will give an overview of the classifier used to perform the automatic measurements and will discuss the experimental results. DATABASE The database consists of solo music pieces played by four different instrument types: classical guitar, violin, trumpet and clarinet. Although publicly available databases for music and instrument classification exist [4], we decided to design and record a new database to be able to: use instruments that cover a wide spectrum in construction type and sound characteristic, have the same piece of music played by different instruments of the same type,
2 investigate the influence of the room on the perception of instrument quality, have all instruments available for recordings and investigations in the future, investigate the influence of different musicians playing the same instrument and use special recording equipment (binaural recording head). For every instrument type we did 600 recordings varying the following conditions: (a) 10 instruments, (b) 2 rooms (anechoic room and reverberant conference room), (c) 3 solo pieces, (d) 5 players and (e) 2 repetitive playings. Solo pieces of approximately 30 seconds were selected that cover a wide range. We used a binaural recording head (MANIKIN II - Cortex Instruments) and a Digital Audio Tape to record the audio signal (48 khz, 16 Bit. The artificial head was placed 2 m in front of the musician. We labelled the recorded signal by a semi-automatic process on note level for supervised training of the classifier. This was done by assigning a unique symbol to each note or group of simultaneously played notes for one recording of each music piece by hand. In a second step these labels where mapped to all recordings of the same piece using dynamic time warping. Finally, all labels where manually checked and corrected if necessary. We believe this database could be valuable for other scientists in this field and plan to make it publicly available for research. SUBJECTIVE EVALUATION Listening experiments were carried out for the recordings of guitars [5][6] and violins [7] so far. The participants were asked to judge the overall quality of the instruments on a MOS scale by listening to the recorded solo pieces. Due to the big number of samples (combinations of instruments, players, pieces and record rooms) two restricted types of listening tests were performed with 32 participants, half of them being players of the considered instrument. The first listening test compares only two instruments under variation of all other recording parameters (2 players, 2 pieces, 2 rooms, 2 repetitions). The second listening test compares all instruments while keeping the other recording parameters fixed. Solo piece MOS Guitar Figure 1.-Interaction diagram that shows the rating of two guitars depending on the played solo piece. A multifactorial variance analysis with repetition of the MO scores revealed the following for the first listening test. The two examined instruments are significantly distinguishable though there are a couple of strong interactions between the other parameters and the instrument. E.g. the combination of instrument and piece significantly changes the MOS, s. Figure 1. This is, however, not surprising as it is conceivable that an instrument is especially suited for a certain kind of music, concert room or even for a certain type of player or listening group. This suggests that there is a complicated dependence of the subjective evaluation on several conditions. 2
3 Consequently it is advisable to keep the recording parameters fixed when trying to distinguish many instruments. The statistical analysis of the second listening test showed that only one out of ten instruments is judged significantly different from most of the others [5]. This holds at least for one choice of recording parameters. However in view of the first listening test it could change for another set of recording parameters. So we conclude instruments are consistently differently judged if either their number is very restricted or the recording conditions are fixed. However due to the fact that all instruments are sort of projected onto a one-dimensional scale, namely the MOS, quite some of them appear to be similar. In other words only extreme instruments are judged significantly different. AUTOMATIC EVALUATION Training Different approaches have been investigated for automatic instrument classification that differ in the features used to describe the important properties of the signal and the classification strategy [8]. A great effort has been made to find suitable feature analysis methods and feature transformations [9][10]. As in speech recognition, mel-scaled features like MFCCs combined with a de-correlation transformation (e.g. PCA) are reported to give good results. Most classification strategies applied so far rely on the typical distribution of static features to distinguish instruments [11][12]. The use of HMM allows modelling of temporal structures that are typical for an instrument [13]. We use our standard HMM based speech recognizer that we already successfully applied to other non-speech classification tasks [14]. Therefore we trained acoustic models for (1) single notes and (2) individual instruments by EM estimation (Viterbi training). First we pass the recordings through a 31 channel mel-scaled filter bank (which slightly outperforms MFCCs in our speech recognizer) and optionally compute the first and second order differences which results in a 63-dimensional primary feature vector. Then we apply a statistical principal component analysis and reduce the feature space to 25 dimensions. Table 1 lists the detailed settings. Table 1.- Experimental setup for automatic classification of guitars and violins. Parameter Guitar Violin Sample rate 16 khz Frame length 25 ms Frame skip 10 ms Primary feat. F0, Energy, 30 channel mel-scaled filter bank Dynamic feat. + - PCA 25 secondary feat. - HMM set 41 notes + silence 36 notes + silence HMM topology 3 states 1 state Gaussian type full covariances CLASSIFICATION We tested two different sets of HMMs. For a first experiment we trained HMMs for all notes occurring in the recordings independently of the instrument and all other conditions described in section 2. The recognition task was to find the most likely sequences of notes for unseen recordings using the Viterbi algorithm. This experiment was intended to check whether the chosen features and HMM setup were suitable for instrument classification. The correctness of the result was assessed by the standard DTW string alignment to the reference label sequence. In a second experiment we trained one HMM set for each instrument independently of all other conditions. Here the recognition task was to identify one out of the ten instruments of one type by an unseen recording. This was done computing the most likely state sequence of the 3
4 recording in all instrument HMM sets and selecting the one with the highest likelihood score. Figure 2 shows the score matrix for violins. This matrix will be evaluated in the next section to unveil similarities between instruments. Table 2.- Experiment 1 - HMM-based note recognition. # GM denotes the number of Gaussian PDFs. # GMs Correctness Accuracy Guitar % 90 % Violin % 93 % Table 3.- Experiment 2 - HMM-based instrument recognition. # GM denotes the number of Gaussian PDFs. # GMs Correctness Guitar % Violin % DISCUSSION The results of experiment 1 listed in Table 1 suggest that the chosen features and HMM setup are suitable for classification of music signals. The recognition of notes played by a violin is more accurate then the recognition using guitar recordings. We found that violins produce a very stable sound within a played note that can be classified easier and has almost no temporal structure. This sound can be sufficiently modelled by one Gaussian assigned to a single HMM state. The fading sound of guitars requires more HMM states and dynamic features to capture the temporal structure of the sound. These findings suggest adapting the classifier setup to the target instrument when building a system for solo music or instrument recognition. The distinction of instruments in experiment 2 based on the scores of 10 independently trained HMM classifiers (experiment 2) works well for both, guitars and violins. Table 3 shows that guitars are easier to identify than violins, although the guitar HMMs comprise less Gaussians than in experiment 1. This result coincides with the subjective impression that the set of guitars in the database cover a broader range of sound characteristics than the set of violins. HMM V10 HMM V9 HMM V8 HMM V7 HMM V6 HMM V5 HMM V4 HMM V3 HMM V2 HMM V1 V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 Figure 2.- Score matrix of experiment 2 - identification of violins - averaged for all samples in the evaluation data set. Dark squares represent high scores. Now we try to find groups of similar instruments based on evaluation of the score matrix yielded in experiment 2 (Figure 2). There is one instrument (violin V3) that is apparently different from all other instruments. Additionally, the cross evaluation scores of the instruments V9 and V10 indicate that these violins might be similar. Unfortunately, we can not verify these findings with results from the subjective evaluations because our listeners were not able to keep the 10 violins apart in the listening experiment (see section 3). At least we know from the instrument description provided by the manufacturer that V9 and V10 are almost identical. 4
5 CONCLUSIONS A convincing subjective evaluation of the quality of instruments is very difficult. There exist distinct interactions between influencing factors. These interactions require a restricted setup of the listening experiments with fixed parameters that takes only different instruments as varying factor into account. The results of these experiments are valid for the chosen set of factors only and cannot be generalized. On the other hand, reliable subjective judgements are essential to answer the questions asked in section 1. The automatic evaluation showed that the distinction of instruments is possible. An open question is still whether score distances are a suitable measure to describe similarities of instruments. Again, extensive subjective evaluations are necessary to answer this question. In the future we will focus on the design and realization of listening experiments. The findings of these evaluations will help to answer the questions posed in section 1. References: [1] E. Meinel, T. Boehm, K. Miklaszewski, and F. Blutner, Estimation of guitar sound quality, Archives of Acoustics, vol. 11, pp , [2] H. Löschke, Differenzierbarkeit von Musikinstrumenten, in Fortschritte der Akustik - DAGA, Braunschweig, March [3] M. Eichner, M. Wolff, and R. Hoffmann, Instrument classification using Hidden Markov Models, in International Symposium on Music Information Retrieval (ISMIR), Victoria, Canada, October [4] M. Goto, H. Hashiguchi, T. Nishimura, and R. Oka, RWC Music Database: music genre database and musical instrument sound database., in 4th International Conference on Music Information Retrieval, 2003, pp [5] S. Merchel, Subjective and objective evaluation of musical instruments on the basis of solo pieces of music (German title: Untersuchungen zur subjektiven und objektiven Beurteilung von Musikinstrumenten anhand von Solomusikstücken) M.S. thesis, Technische Universität Dresden, Fakultät Elektrotechnik und Informationstechnik, Institut für Akustik und Sprachkommunikation, [6] S. Merchel and R. Hoffmann, Subjective evaluation of musical instruments on the basis of solo pieces of music, in Second ISCA/DEGA Tutorial and Research Workshop on Perceptual Quality of Systems, Berlin, September [7] S. Hübler, Subjective and objective evaluation of violins on the basis of solo pieces of music (German title: Untersuchungen zur subjektiven und objektiven Bewertung und Beurteilung von Geigen anhand von Solomusikstücken) Studienarbeit, Technische Universität Dresden, Fakultät Elektrotechnik und Informationstechnik, Institut für Akustik und Sprachkommunikation, [8] P. Herrera-Boyer, X. Amatriain, E. Batlle, and X. Serra, Towards Instrument Segmentation for Music Content Description: a Critical Review of Instrument Classification Techniques, in 1st International Conference on Music Information Retrieval, [9] Antti Eronen, Comparision of features for musical instrument recognition, in Proceedings WASPAA 2001 (IEEE Workshop on Applications of Signal Processing to Audio and Acoustics), [10] Judith C. Brown, Olivier Houix, and StephenMcAdams, Feature dependence in the automatic identification of musical woodwind instruments, in The Journal of the Acoustical Society of America, March 2001, vol. 109, pp [11] K. Martin, Musical instrument identification: A pattern-recognition approach, in Paper read at the 136 th meeting of the Acoustical Society of America, [12] A.G. Krishna and T.V. Sreenivas, Music instrument recognition: from isolated notes to solo phrases, in Proceedings ICASSP-04 (IEEE International Conference on Acoustics, Speech and Signal Processing), [13] Antti Eronen, Musical instrument recognition using ICA-based transform of features and discriminatively trained HMMs, in Proceedings ICASSP-03 (IEEE International Conference on Acoustics, Speech and Signal Processing), [14] C. Tschöpe, D. Hentschel, M. Eichner, M. Wolff, and R. Hoffmann, Classification of non-speech acoustic signals using structure models, in Proc. IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr. 2004, Montreal, Canada. 5
Drum Sound Identification for Polyphonic Music Using Template Adaptation and Matching Methods
Drum Sound Identification for Polyphonic Music Using Template Adaptation and Matching Methods Kazuyoshi Yoshii, Masataka Goto and Hiroshi G. Okuno Department of Intelligence Science and Technology National
More informationMUSICAL INSTRUMENT IDENTIFICATION BASED ON HARMONIC TEMPORAL TIMBRE FEATURES
MUSICAL INSTRUMENT IDENTIFICATION BASED ON HARMONIC TEMPORAL TIMBRE FEATURES Jun Wu, Yu Kitano, Stanislaw Andrzej Raczynski, Shigeki Miyabe, Takuya Nishimoto, Nobutaka Ono and Shigeki Sagayama The Graduate
More informationSemi-supervised Musical Instrument Recognition
Semi-supervised Musical Instrument Recognition Master s Thesis Presentation Aleksandr Diment 1 1 Tampere niversity of Technology, Finland Supervisors: Adj.Prof. Tuomas Virtanen, MSc Toni Heittola 17 May
More informationInstrument Recognition in Polyphonic Mixtures Using Spectral Envelopes
Instrument Recognition in Polyphonic Mixtures Using Spectral Envelopes hello Jay Biernat Third author University of Rochester University of Rochester Affiliation3 words jbiernat@ur.rochester.edu author3@ismir.edu
More informationA QUERY BY EXAMPLE MUSIC RETRIEVAL ALGORITHM
A QUER B EAMPLE MUSIC RETRIEVAL ALGORITHM H. HARB AND L. CHEN Maths-Info department, Ecole Centrale de Lyon. 36, av. Guy de Collongue, 69134, Ecully, France, EUROPE E-mail: {hadi.harb, liming.chen}@ec-lyon.fr
More informationTranscription of the Singing Melody in Polyphonic Music
Transcription of the Singing Melody in Polyphonic Music Matti Ryynänen and Anssi Klapuri Institute of Signal Processing, Tampere University Of Technology P.O.Box 553, FI-33101 Tampere, Finland {matti.ryynanen,
More informationTopics in Computer Music Instrument Identification. Ioanna Karydi
Topics in Computer Music Instrument Identification Ioanna Karydi Presentation overview What is instrument identification? Sound attributes & Timbre Human performance The ideal algorithm Selected approaches
More informationInternational Journal of Advance Engineering and Research Development MUSICAL INSTRUMENT IDENTIFICATION AND STATUS FINDING WITH MFCC
Scientific Journal of Impact Factor (SJIF): 5.71 International Journal of Advance Engineering and Research Development Volume 5, Issue 04, April -2018 e-issn (O): 2348-4470 p-issn (P): 2348-6406 MUSICAL
More informationA System for Automatic Chord Transcription from Audio Using Genre-Specific Hidden Markov Models
A System for Automatic Chord Transcription from Audio Using Genre-Specific Hidden Markov Models Kyogu Lee Center for Computer Research in Music and Acoustics Stanford University, Stanford CA 94305, USA
More informationMUSI-6201 Computational Music Analysis
MUSI-6201 Computational Music Analysis Part 9.1: Genre Classification alexander lerch November 4, 2015 temporal analysis overview text book Chapter 8: Musical Genre, Similarity, and Mood (pp. 151 155)
More informationClassification of Musical Instruments sounds by Using MFCC and Timbral Audio Descriptors
Classification of Musical Instruments sounds by Using MFCC and Timbral Audio Descriptors Priyanka S. Jadhav M.E. (Computer Engineering) G. H. Raisoni College of Engg. & Mgmt. Wagholi, Pune, India E-mail:
More informationAn Accurate Timbre Model for Musical Instruments and its Application to Classification
An Accurate Timbre Model for Musical Instruments and its Application to Classification Juan José Burred 1,AxelRöbel 2, and Xavier Rodet 2 1 Communication Systems Group, Technical University of Berlin,
More informationAutomatic Identification of Instrument Type in Music Signal using Wavelet and MFCC
Automatic Identification of Instrument Type in Music Signal using Wavelet and MFCC Arijit Ghosal, Rudrasis Chakraborty, Bibhas Chandra Dhara +, and Sanjoy Kumar Saha! * CSE Dept., Institute of Technology
More informationSubjective Similarity of Music: Data Collection for Individuality Analysis
Subjective Similarity of Music: Data Collection for Individuality Analysis Shota Kawabuchi and Chiyomi Miyajima and Norihide Kitaoka and Kazuya Takeda Nagoya University, Nagoya, Japan E-mail: shota.kawabuchi@g.sp.m.is.nagoya-u.ac.jp
More informationAutomatic Labelling of tabla signals
ISMIR 2003 Oct. 27th 30th 2003 Baltimore (USA) Automatic Labelling of tabla signals Olivier K. GILLET, Gaël RICHARD Introduction Exponential growth of available digital information need for Indexing and
More informationClassification of Timbre Similarity
Classification of Timbre Similarity Corey Kereliuk McGill University March 15, 2007 1 / 16 1 Definition of Timbre What Timbre is Not What Timbre is A 2-dimensional Timbre Space 2 3 Considerations Common
More informationAutomatic Laughter Detection
Automatic Laughter Detection Mary Knox Final Project (EECS 94) knoxm@eecs.berkeley.edu December 1, 006 1 Introduction Laughter is a powerful cue in communication. It communicates to listeners the emotional
More informationTHE importance of music content analysis for musical
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 15, NO. 1, JANUARY 2007 333 Drum Sound Recognition for Polyphonic Audio Signals by Adaptation and Matching of Spectrogram Templates With
More informationPOLYPHONIC INSTRUMENT RECOGNITION USING SPECTRAL CLUSTERING
POLYPHONIC INSTRUMENT RECOGNITION USING SPECTRAL CLUSTERING Luis Gustavo Martins Telecommunications and Multimedia Unit INESC Porto Porto, Portugal lmartins@inescporto.pt Juan José Burred Communication
More informationTOWARD AN INTELLIGENT EDITOR FOR JAZZ MUSIC
TOWARD AN INTELLIGENT EDITOR FOR JAZZ MUSIC G.TZANETAKIS, N.HU, AND R.B. DANNENBERG Computer Science Department, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213, USA E-mail: gtzan@cs.cmu.edu
More informationMusical Instrument Identification based on F0-dependent Multivariate Normal Distribution
Musical Instrument Identification based on F0-dependent Multivariate Normal Distribution Tetsuro Kitahara* Masataka Goto** Hiroshi G. Okuno* *Grad. Sch l of Informatics, Kyoto Univ. **PRESTO JST / Nat
More informationMusical Instrument Identification Using Principal Component Analysis and Multi-Layered Perceptrons
Musical Instrument Identification Using Principal Component Analysis and Multi-Layered Perceptrons Róisín Loughran roisin.loughran@ul.ie Jacqueline Walker jacqueline.walker@ul.ie Michael O Neill University
More informationINTER GENRE SIMILARITY MODELLING FOR AUTOMATIC MUSIC GENRE CLASSIFICATION
INTER GENRE SIMILARITY MODELLING FOR AUTOMATIC MUSIC GENRE CLASSIFICATION ULAŞ BAĞCI AND ENGIN ERZIN arxiv:0907.3220v1 [cs.sd] 18 Jul 2009 ABSTRACT. Music genre classification is an essential tool for
More informationEE391 Special Report (Spring 2005) Automatic Chord Recognition Using A Summary Autocorrelation Function
EE391 Special Report (Spring 25) Automatic Chord Recognition Using A Summary Autocorrelation Function Advisor: Professor Julius Smith Kyogu Lee Center for Computer Research in Music and Acoustics (CCRMA)
More informationSupervised Musical Source Separation from Mono and Stereo Mixtures based on Sinusoidal Modeling
Supervised Musical Source Separation from Mono and Stereo Mixtures based on Sinusoidal Modeling Juan José Burred Équipe Analyse/Synthèse, IRCAM burred@ircam.fr Communication Systems Group Technische Universität
More informationRecognising Cello Performers using Timbre Models
Recognising Cello Performers using Timbre Models Chudy, Magdalena; Dixon, Simon For additional information about this publication click this link. http://qmro.qmul.ac.uk/jspui/handle/123456789/5013 Information
More informationThe quality of potato chip sounds and crispness impression
PROCEEDINGS of the 22 nd International Congress on Acoustics Product Quality and Multimodal Interaction: Paper ICA2016-558 The quality of potato chip sounds and crispness impression M. Ercan Altinsoy Chair
More informationSinger Traits Identification using Deep Neural Network
Singer Traits Identification using Deep Neural Network Zhengshan Shi Center for Computer Research in Music and Acoustics Stanford University kittyshi@stanford.edu Abstract The author investigates automatic
More informationApplication Of Missing Feature Theory To The Recognition Of Musical Instruments In Polyphonic Audio
Application Of Missing Feature Theory To The Recognition Of Musical Instruments In Polyphonic Audio Jana Eggink and Guy J. Brown Department of Computer Science, University of Sheffield Regent Court, 11
More informationImproving Frame Based Automatic Laughter Detection
Improving Frame Based Automatic Laughter Detection Mary Knox EE225D Class Project knoxm@eecs.berkeley.edu December 13, 2007 Abstract Laughter recognition is an underexplored area of research. My goal for
More informationModeling memory for melodies
Modeling memory for melodies Daniel Müllensiefen 1 and Christian Hennig 2 1 Musikwissenschaftliches Institut, Universität Hamburg, 20354 Hamburg, Germany 2 Department of Statistical Science, University
More informationChord Classification of an Audio Signal using Artificial Neural Network
Chord Classification of an Audio Signal using Artificial Neural Network Ronesh Shrestha Student, Department of Electrical and Electronic Engineering, Kathmandu University, Dhulikhel, Nepal ---------------------------------------------------------------------***---------------------------------------------------------------------
More informationAutomatic Rhythmic Notation from Single Voice Audio Sources
Automatic Rhythmic Notation from Single Voice Audio Sources Jack O Reilly, Shashwat Udit Introduction In this project we used machine learning technique to make estimations of rhythmic notation of a sung
More informationWE ADDRESS the development of a novel computational
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 3, MARCH 2010 663 Dynamic Spectral Envelope Modeling for Timbre Analysis of Musical Instrument Sounds Juan José Burred, Member,
More informationMUSICAL INSTRUMENT RECOGNITION WITH WAVELET ENVELOPES
MUSICAL INSTRUMENT RECOGNITION WITH WAVELET ENVELOPES PACS: 43.60.Lq Hacihabiboglu, Huseyin 1,2 ; Canagarajah C. Nishan 2 1 Sonic Arts Research Centre (SARC) School of Computer Science Queen s University
More informationMusic Genre Classification and Variance Comparison on Number of Genres
Music Genre Classification and Variance Comparison on Number of Genres Miguel Francisco, miguelf@stanford.edu Dong Myung Kim, dmk8265@stanford.edu 1 Abstract In this project we apply machine learning techniques
More informationSinging voice synthesis based on deep neural networks
INTERSPEECH 2016 September 8 12, 2016, San Francisco, USA Singing voice synthesis based on deep neural networks Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
More informationHidden Markov Model based dance recognition
Hidden Markov Model based dance recognition Dragutin Hrenek, Nenad Mikša, Robert Perica, Pavle Prentašić and Boris Trubić University of Zagreb, Faculty of Electrical Engineering and Computing Unska 3,
More informationinter.noise 2000 The 29th International Congress and Exhibition on Noise Control Engineering August 2000, Nice, FRANCE
Copyright SFA - InterNoise 2000 1 inter.noise 2000 The 29th International Congress and Exhibition on Noise Control Engineering 27-30 August 2000, Nice, FRANCE I-INCE Classification: 7.9 THE FUTURE OF SOUND
More informationRecognising Cello Performers Using Timbre Models
Recognising Cello Performers Using Timbre Models Magdalena Chudy and Simon Dixon Abstract In this paper, we compare timbre features of various cello performers playing the same instrument in solo cello
More informationPhone-based Plosive Detection
Phone-based Plosive Detection 1 Andreas Madsack, Grzegorz Dogil, Stefan Uhlich, Yugu Zeng and Bin Yang Abstract We compare two segmentation approaches to plosive detection: One aproach is using a uniform
More informationABSOLUTE OR RELATIVE? A NEW APPROACH TO BUILDING FEATURE VECTORS FOR EMOTION TRACKING IN MUSIC
ABSOLUTE OR RELATIVE? A NEW APPROACH TO BUILDING FEATURE VECTORS FOR EMOTION TRACKING IN MUSIC Vaiva Imbrasaitė, Peter Robinson Computer Laboratory, University of Cambridge, UK Vaiva.Imbrasaite@cl.cam.ac.uk
More informationAvailable online at ScienceDirect. Procedia Computer Science 46 (2015 )
Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 46 (2015 ) 381 387 International Conference on Information and Communication Technologies (ICICT 2014) Music Information
More informationMusical instrument identification in continuous recordings
Musical instrument identification in continuous recordings Arie Livshin, Xavier Rodet To cite this version: Arie Livshin, Xavier Rodet. Musical instrument identification in continuous recordings. Digital
More informationA New Method for Calculating Music Similarity
A New Method for Calculating Music Similarity Eric Battenberg and Vijay Ullal December 12, 2006 Abstract We introduce a new technique for calculating the perceived similarity of two songs based on their
More informationAUTOREGRESSIVE MFCC MODELS FOR GENRE CLASSIFICATION IMPROVED BY HARMONIC-PERCUSSION SEPARATION
AUTOREGRESSIVE MFCC MODELS FOR GENRE CLASSIFICATION IMPROVED BY HARMONIC-PERCUSSION SEPARATION Halfdan Rump, Shigeki Miyabe, Emiru Tsunoo, Nobukata Ono, Shigeki Sagama The University of Tokyo, Graduate
More informationSupervised Learning in Genre Classification
Supervised Learning in Genre Classification Introduction & Motivation Mohit Rajani and Luke Ekkizogloy {i.mohit,luke.ekkizogloy}@gmail.com Stanford University, CS229: Machine Learning, 2009 Now that music
More informationProceedings of Meetings on Acoustics
Proceedings of Meetings on Acoustics Volume 19, 2013 http://acousticalsociety.org/ ICA 2013 Montreal Montreal, Canada 2-7 June 2013 Musical Acoustics Session 3pMU: Perception and Orchestration Practice
More informationA PERPLEXITY BASED COVER SONG MATCHING SYSTEM FOR SHORT LENGTH QUERIES
12th International Society for Music Information Retrieval Conference (ISMIR 2011) A PERPLEXITY BASED COVER SONG MATCHING SYSTEM FOR SHORT LENGTH QUERIES Erdem Unal 1 Elaine Chew 2 Panayiotis Georgiou
More informationPiano Transcription MUMT611 Presentation III 1 March, Hankinson, 1/15
Piano Transcription MUMT611 Presentation III 1 March, 2007 Hankinson, 1/15 Outline Introduction Techniques Comb Filtering & Autocorrelation HMMs Blackboard Systems & Fuzzy Logic Neural Networks Examples
More informationMultiple instrument tracking based on reconstruction error, pitch continuity and instrument activity
Multiple instrument tracking based on reconstruction error, pitch continuity and instrument activity Holger Kirchhoff 1, Simon Dixon 1, and Anssi Klapuri 2 1 Centre for Digital Music, Queen Mary University
More informationThe Human Features of Music.
The Human Features of Music. Bachelor Thesis Artificial Intelligence, Social Studies, Radboud University Nijmegen Chris Kemper, s4359410 Supervisor: Makiko Sadakata Artificial Intelligence, Social Studies,
More informationComputational Modelling of Harmony
Computational Modelling of Harmony Simon Dixon Centre for Digital Music, Queen Mary University of London, Mile End Rd, London E1 4NS, UK simon.dixon@elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/simond
More informationA CHROMA-BASED SALIENCE FUNCTION FOR MELODY AND BASS LINE ESTIMATION FROM MUSIC AUDIO SIGNALS
A CHROMA-BASED SALIENCE FUNCTION FOR MELODY AND BASS LINE ESTIMATION FROM MUSIC AUDIO SIGNALS Justin Salamon Music Technology Group Universitat Pompeu Fabra, Barcelona, Spain justin.salamon@upf.edu Emilia
More informationAutomatic Laughter Detection
Automatic Laughter Detection Mary Knox 1803707 knoxm@eecs.berkeley.edu December 1, 006 Abstract We built a system to automatically detect laughter from acoustic features of audio. To implement the system,
More informationMusical Instrument Recognizer Instrogram and Its Application to Music Retrieval based on Instrumentation Similarity
Musical Instrument Recognizer Instrogram and Its Application to Music Retrieval based on Instrumentation Similarity Tetsuro Kitahara, Masataka Goto, Kazunori Komatani, Tetsuya Ogata and Hiroshi G. Okuno
More informationOn human capability and acoustic cues for discriminating singing and speaking voices
Alma Mater Studiorum University of Bologna, August 22-26 2006 On human capability and acoustic cues for discriminating singing and speaking voices Yasunori Ohishi Graduate School of Information Science,
More informationMusic Information Retrieval Community
Music Information Retrieval Community What: Developing systems that retrieve music When: Late 1990 s to Present Where: ISMIR - conference started in 2000 Why: lots of digital music, lots of music lovers,
More informationMusic Recommendation from Song Sets
Music Recommendation from Song Sets Beth Logan Cambridge Research Laboratory HP Laboratories Cambridge HPL-2004-148 August 30, 2004* E-mail: Beth.Logan@hp.com music analysis, information retrieval, multimedia
More informationDETECTION OF SLOW-MOTION REPLAY SEGMENTS IN SPORTS VIDEO FOR HIGHLIGHTS GENERATION
DETECTION OF SLOW-MOTION REPLAY SEGMENTS IN SPORTS VIDEO FOR HIGHLIGHTS GENERATION H. Pan P. van Beek M. I. Sezan Electrical & Computer Engineering University of Illinois Urbana, IL 6182 Sharp Laboratories
More informationMODELS of music begin with a representation of the
602 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 3, MARCH 2010 Modeling Music as a Dynamic Texture Luke Barrington, Student Member, IEEE, Antoni B. Chan, Member, IEEE, and
More informationEffects of acoustic degradations on cover song recognition
Signal Processing in Acoustics: Paper 68 Effects of acoustic degradations on cover song recognition Julien Osmalskyj (a), Jean-Jacques Embrechts (b) (a) University of Liège, Belgium, josmalsky@ulg.ac.be
More informationA SCORE-INFORMED PIANO TUTORING SYSTEM WITH MISTAKE DETECTION AND SCORE SIMPLIFICATION
A SCORE-INFORMED PIANO TUTORING SYSTEM WITH MISTAKE DETECTION AND SCORE SIMPLIFICATION Tsubasa Fukuda Yukara Ikemiya Katsutoshi Itoyama Kazuyoshi Yoshii Graduate School of Informatics, Kyoto University
More informationpitch estimation and instrument identification by joint modeling of sustained and attack sounds.
Polyphonic pitch estimation and instrument identification by joint modeling of sustained and attack sounds Jun Wu, Emmanuel Vincent, Stanislaw Raczynski, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama
More informationSpeech and Speaker Recognition for the Command of an Industrial Robot
Speech and Speaker Recognition for the Command of an Industrial Robot CLAUDIA MOISA*, HELGA SILAGHI*, ANDREI SILAGHI** *Dept. of Electric Drives and Automation University of Oradea University Street, nr.
More informationHIT SONG SCIENCE IS NOT YET A SCIENCE
HIT SONG SCIENCE IS NOT YET A SCIENCE François Pachet Sony CSL pachet@csl.sony.fr Pierre Roy Sony CSL roy@csl.sony.fr ABSTRACT We describe a large-scale experiment aiming at validating the hypothesis that
More informationSubjective evaluation of common singing skills using the rank ordering method
lma Mater Studiorum University of ologna, ugust 22-26 2006 Subjective evaluation of common singing skills using the rank ordering method Tomoyasu Nakano Graduate School of Library, Information and Media
More informationAcoustic Scene Classification
Acoustic Scene Classification Marc-Christoph Gerasch Seminar Topics in Computer Music - Acoustic Scene Classification 6/24/2015 1 Outline Acoustic Scene Classification - definition History and state of
More informationTRACKING THE ODD : METER INFERENCE IN A CULTURALLY DIVERSE MUSIC CORPUS
TRACKING THE ODD : METER INFERENCE IN A CULTURALLY DIVERSE MUSIC CORPUS Andre Holzapfel New York University Abu Dhabi andre@rhythmos.org Florian Krebs Johannes Kepler University Florian.Krebs@jku.at Ajay
More informationIMPROVING MARKOV MODEL-BASED MUSIC PIECE STRUCTURE LABELLING WITH ACOUSTIC INFORMATION
IMPROVING MAROV MODEL-BASED MUSIC PIECE STRUCTURE LABELLING WITH ACOUSTIC INFORMATION Jouni Paulus Fraunhofer Institute for Integrated Circuits IIS Erlangen, Germany jouni.paulus@iis.fraunhofer.de ABSTRACT
More informationSinger Identification
Singer Identification Bertrand SCHERRER McGill University March 15, 2007 Bertrand SCHERRER (McGill University) Singer Identification March 15, 2007 1 / 27 Outline 1 Introduction Applications Challenges
More informationThe song remains the same: identifying versions of the same piece using tonal descriptors
The song remains the same: identifying versions of the same piece using tonal descriptors Emilia Gómez Music Technology Group, Universitat Pompeu Fabra Ocata, 83, Barcelona emilia.gomez@iua.upf.edu Abstract
More informationA System for Acoustic Chord Transcription and Key Extraction from Audio Using Hidden Markov models Trained on Synthesized Audio
Curriculum Vitae Kyogu Lee Advanced Technology Center, Gracenote Inc. 2000 Powell Street, Suite 1380 Emeryville, CA 94608 USA Tel) 1-510-428-7296 Fax) 1-510-547-9681 klee@gracenote.com kglee@ccrma.stanford.edu
More informationGYROPHONE RECOGNIZING SPEECH FROM GYROSCOPE SIGNALS. Yan Michalevsky (1), Gabi Nakibly (2) and Dan Boneh (1)
GYROPHONE RECOGNIZING SPEECH FROM GYROSCOPE SIGNALS Yan Michalevsky (1), Gabi Nakibly (2) and Dan Boneh (1) (1) Stanford University (2) National Research and Simulation Center, Rafael Ltd. 0 MICROPHONE
More informationPredicting Time-Varying Musical Emotion Distributions from Multi-Track Audio
Predicting Time-Varying Musical Emotion Distributions from Multi-Track Audio Jeffrey Scott, Erik M. Schmidt, Matthew Prockup, Brandon Morton, and Youngmoo E. Kim Music and Entertainment Technology Laboratory
More informationGRADIENT-BASED MUSICAL FEATURE EXTRACTION BASED ON SCALE-INVARIANT FEATURE TRANSFORM
19th European Signal Processing Conference (EUSIPCO 2011) Barcelona, Spain, August 29 - September 2, 2011 GRADIENT-BASED MUSICAL FEATURE EXTRACTION BASED ON SCALE-INVARIANT FEATURE TRANSFORM Tomoko Matsui
More informationNarrative Theme Navigation for Sitcoms Supported by Fan-generated Scripts
Narrative Theme Navigation for Sitcoms Supported by Fan-generated Scripts Gerald Friedland, Luke Gottlieb, Adam Janin International Computer Science Institute (ICSI) Presented by: Katya Gonina What? Novel
More informationHIDDEN MARKOV MODELS FOR SPECTRAL SIMILARITY OF SONGS. Arthur Flexer, Elias Pampalk, Gerhard Widmer
Proc. of the 8 th Int. Conference on Digital Audio Effects (DAFx 5), Madrid, Spain, September 2-22, 25 HIDDEN MARKOV MODELS FOR SPECTRAL SIMILARITY OF SONGS Arthur Flexer, Elias Pampalk, Gerhard Widmer
More informationRetrieval of textual song lyrics from sung inputs
INTERSPEECH 2016 September 8 12, 2016, San Francisco, USA Retrieval of textual song lyrics from sung inputs Anna M. Kruspe Fraunhofer IDMT, Ilmenau, Germany kpe@idmt.fraunhofer.de Abstract Retrieving the
More informationA Study of Synchronization of Audio Data with Symbolic Data. Music254 Project Report Spring 2007 SongHui Chon
A Study of Synchronization of Audio Data with Symbolic Data Music254 Project Report Spring 2007 SongHui Chon Abstract This paper provides an overview of the problem of audio and symbolic synchronization.
More informationMusic Segmentation Using Markov Chain Methods
Music Segmentation Using Markov Chain Methods Paul Finkelstein March 8, 2011 Abstract This paper will present just how far the use of Markov Chains has spread in the 21 st century. We will explain some
More informationPredicting Performance of PESQ in Case of Single Frame Losses
Predicting Performance of PESQ in Case of Single Frame Losses Christian Hoene, Enhtuya Dulamsuren-Lalla Technical University of Berlin, Germany Fax: +49 30 31423819 Email: hoene@ieee.org Abstract ITU s
More informationA SEGMENTAL SPECTRO-TEMPORAL MODEL OF MUSICAL TIMBRE
A SEGMENTAL SPECTRO-TEMPORAL MODEL OF MUSICAL TIMBRE Juan José Burred, Axel Röbel Analysis/Synthesis Team, IRCAM Paris, France {burred,roebel}@ircam.fr ABSTRACT We propose a new statistical model of musical
More informationA FUNCTIONAL CLASSIFICATION OF ONE INSTRUMENT S TIMBRES
A FUNCTIONAL CLASSIFICATION OF ONE INSTRUMENT S TIMBRES Panayiotis Kokoras School of Music Studies Aristotle University of Thessaloniki email@panayiotiskokoras.com Abstract. This article proposes a theoretical
More informationAutomatic music transcription
Music transcription 1 Music transcription 2 Automatic music transcription Sources: * Klapuri, Introduction to music transcription, 2006. www.cs.tut.fi/sgn/arg/klap/amt-intro.pdf * Klapuri, Eronen, Astola:
More informationA NOVEL CEPSTRAL REPRESENTATION FOR TIMBRE MODELING OF SOUND SOURCES IN POLYPHONIC MIXTURES
A NOVEL CEPSTRAL REPRESENTATION FOR TIMBRE MODELING OF SOUND SOURCES IN POLYPHONIC MIXTURES Zhiyao Duan 1, Bryan Pardo 2, Laurent Daudet 3 1 Department of Electrical and Computer Engineering, University
More informationAutomatic Extraction of Popular Music Ringtones Based on Music Structure Analysis
Automatic Extraction of Popular Music Ringtones Based on Music Structure Analysis Fengyan Wu fengyanyy@163.com Shutao Sun stsun@cuc.edu.cn Weiyao Xue Wyxue_std@163.com Abstract Automatic extraction of
More informationPopular Song Summarization Using Chorus Section Detection from Audio Signal
Popular Song Summarization Using Chorus Section Detection from Audio Signal Sheng GAO 1 and Haizhou LI 2 Institute for Infocomm Research, A*STAR, Singapore 1 gaosheng@i2r.a-star.edu.sg 2 hli@i2r.a-star.edu.sg
More informationA Bayesian Network for Real-Time Musical Accompaniment
A Bayesian Network for Real-Time Musical Accompaniment Christopher Raphael Department of Mathematics and Statistics, University of Massachusetts at Amherst, Amherst, MA 01003-4515, raphael~math.umass.edu
More informationCS229 Project Report Polyphonic Piano Transcription
CS229 Project Report Polyphonic Piano Transcription Mohammad Sadegh Ebrahimi Stanford University Jean-Baptiste Boin Stanford University sadegh@stanford.edu jbboin@stanford.edu 1. Introduction In this project
More informationA Bootstrap Method for Training an Accurate Audio Segmenter
A Bootstrap Method for Training an Accurate Audio Segmenter Ning Hu and Roger B. Dannenberg Computer Science Department Carnegie Mellon University 5000 Forbes Ave Pittsburgh, PA 1513 {ninghu,rbd}@cs.cmu.edu
More informationinter.noise 2000 The 29th International Congress and Exhibition on Noise Control Engineering August 2000, Nice, FRANCE
Copyright SFA - InterNoise 2000 1 inter.noise 2000 The 29th International Congress and Exhibition on Noise Control Engineering 27-30 August 2000, Nice, FRANCE I-INCE Classification: 6.1 INFLUENCE OF THE
More informationComputational Models of Music Similarity. Elias Pampalk National Institute for Advanced Industrial Science and Technology (AIST)
Computational Models of Music Similarity 1 Elias Pampalk National Institute for Advanced Industrial Science and Technology (AIST) Abstract The perceived similarity of two pieces of music is multi-dimensional,
More informationInteractive Classification of Sound Objects for Polyphonic Electro-Acoustic Music Annotation
for Polyphonic Electro-Acoustic Music Annotation Sebastien Gulluni 2, Slim Essid 2, Olivier Buisson, and Gaël Richard 2 Institut National de l Audiovisuel, 4 avenue de l Europe 94366 Bry-sur-marne Cedex,
More informationDetection of Panoramic Takes in Soccer Videos Using Phase Correlation and Boosting
Detection of Panoramic Takes in Soccer Videos Using Phase Correlation and Boosting Luiz G. L. B. M. de Vasconcelos Research & Development Department Globo TV Network Email: luiz.vasconcelos@tvglobo.com.br
More informationAUTOM AT I C DRUM SOUND DE SCRI PT I ON FOR RE AL - WORL D M USI C USING TEMPLATE ADAPTATION AND MATCHING METHODS
Proceedings of the 5th International Conference on Music Information Retrieval (ISMIR 2004), pp.184-191, October 2004. AUTOM AT I C DRUM SOUND DE SCRI PT I ON FOR RE AL - WORL D M USI C USING TEMPLATE
More informationJOINT BEAT AND DOWNBEAT TRACKING WITH RECURRENT NEURAL NETWORKS
JOINT BEAT AND DOWNBEAT TRACKING WITH RECURRENT NEURAL NETWORKS Sebastian Böck, Florian Krebs, and Gerhard Widmer Department of Computational Perception Johannes Kepler University Linz, Austria sebastian.boeck@jku.at
More informationMUSICAL INSTRUMENT RECOGNITION USING BIOLOGICALLY INSPIRED FILTERING OF TEMPORAL DICTIONARY ATOMS
MUSICAL INSTRUMENT RECOGNITION USING BIOLOGICALLY INSPIRED FILTERING OF TEMPORAL DICTIONARY ATOMS Steven K. Tjoa and K. J. Ray Liu Signals and Information Group, Department of Electrical and Computer Engineering
More informationWipe Scene Change Detection in Video Sequences
Wipe Scene Change Detection in Video Sequences W.A.C. Fernando, C.N. Canagarajah, D. R. Bull Image Communications Group, Centre for Communications Research, University of Bristol, Merchant Ventures Building,
More informationTOWARD UNDERSTANDING EXPRESSIVE PERCUSSION THROUGH CONTENT BASED ANALYSIS
TOWARD UNDERSTANDING EXPRESSIVE PERCUSSION THROUGH CONTENT BASED ANALYSIS Matthew Prockup, Erik M. Schmidt, Jeffrey Scott, and Youngmoo E. Kim Music and Entertainment Technology Laboratory (MET-lab) Electrical
More information