Arie Livshin - Academia.edu (original) (raw)

Papers by Arie Livshin

HAL (Le Centre pour la Communication Scientifique Directe), 2009

Abstract—Compilation of musical instrument sample databases requires careful elimination of badly... more Abstract—Compilation of musical instrument sample databases requires careful elimination of badly recorded samples and validation of sample classification into correct categories. This paper introduces algorithms for automatic removal of bad instrument samples using Automatic Musical Instrument Recognition and Outlier Detection techniques. Best evaluation results on a methodically contaminated sound database are achieved using the introduced MCIQR method, which removes 70.1 % “bad ” samples with 0.9% false-alarm rate and 90.4 % with 8.8 % false-alarm rate. Index Terms—Instrument recognition, multimedia databases, music, music information retrieval, pattern classification.

This convention paper has been reproduced from the author's advance manuscript, without edit... more This convention paper has been reproduced from the author's advance manuscript, without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for the contents. Additional papers may be obtained by sending request

In numerous articles (Martin and Kim, 1998; Fraser and Fujinaga, 1999; and many others) sound cla... more In numerous articles (Martin and Kim, 1998; Fraser and Fujinaga, 1999; and many others) sound classification algorithms are evaluated using "self classification "- the learning and test groups are randomly selected out of the same sound database. We will show that "self classification " is not necessarily a good statistic for the ability of a classification algorithm to learn, generalize or classify well. We introduce the alternative "Minus-1 DB " evaluation method and demonstrate that it does not have the shortcomings of "self classification". 1 Testing Platform The importance of cross database evaluation will be demonstrated through a variety of classification experiments. 1.1 The Test Set The Sounds. In order to demonstrate well the claims in the paper, we extracted out of 5 sound databases, recorded in various acoustic conditions and different equipment, the samples of 7 instruments common to them, played with a "standard " playi...

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific ... more HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Recognition of musical instruments in multi-instrumental, polyphonic music, is a difficult challe... more Recognition of musical instruments in multi-instrumental, polyphonic music, is a difficult challenge which is yet far from being solved. Successful instrument recognition techniques in solos (monophonic or polyphonic recordings of single instruments) can help to deal with this task. We introduce an instrument recognition process in solo recordings of a set of instruments (bassoon, clarinet, flute, guitar, piano, cello and violin), which yields a high recognition rate. A large and very diverse solo database (108 different solos, all by different performers) is used in order to encompass the different sound possibilities of each instrument and evaluate the generalization ability of the classification process. First we bring classification results using a very extensive collection of features (62 different feature types), and then use our GDE feature selection algorithm to select a smaller feature set with a relatively short computation time, which allows us to perform instrument recog...

Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the... more Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the nonharmonic Residual. It is common to treat the Harmonic Series as the main characteristic of the timbre of pitched musical instruments. But does the Harmonic Series indeed contain the complete information required for discriminating among different musical instruments? Could the non-harmonic Residual, the “noise”, be used all by itself for instrument recognition? The paper begins by performing musical instrument recognition with an extensive sound collection using a large set of feature descriptors, achieving a high instrument recognition rate. Next, using Additive Analysis/Synthesis, each sound sample is resynthesized using solely its Harmonic Series. These “Harmonic ” samples are then subtracted from the original samples to retrieve the non-harmonic Residuals. Instrument recognition is performed on the resynthesized and the “Residual ” sound sets. The paper shows that the Harmonic Se...

Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the... more Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the nonharmonic Residual. It is common to treat the Harmonic Series as the main characteristic of the timbre of pitched musical instruments. But does the Harmonic Series indeed contain the complete information required for discriminating among different musical instruments? Could the non-harmonic Residual, the “noise”, be used all by itself for instrument recognition? The paper begins by performing musical instrument recognition with an extensive sound collection using a large set of feature descriptors, achieving a high instrument recognition rate. Next, using Additive Analysis/Synthesis, each sound sample is resynthesized using solely its Harmonic Series. These “Harmonic” samples are then subtracted from the original samples to retrieve the non-harmonic Residuals. Instrument recognition is performed on the resynthesized and the “Residual” sound sets. The paper shows that the Harmonic Seri...

In this article we shall deal with automatic classification of sound samples and ways to improve ... more In this article we shall deal with automatic classification of sound samples and ways to improve the classification results: We describe a classification process which produces high classification success percentage (over 95% for musical instruments) and compare the results of three classification algorithms: Multidimensional Gauss, KNN and LVQ. Next, we introduce several algorithms to improve the sound database self-consistency by removing outliers: LOO, IQR and MIQR. We present our efficient process for Gradual Elimination of Descriptors using Discriminant Analysis (GDE) which improves a previous descriptor selection algorithm (Peeters and Rodet 2002). It also enables us to reduce the computation complexity and space requirements of a sound classification process according to specific accuracy needs. Moreover, it allows finding the dominant separating characteristics of the sound samples in a database according to classification taxonomy. The article ends by showing that good clas...

Recognition of musical instruments in multi-instrumental, polyphonic music is a difficult challen... more Recognition of musical instruments in multi-instrumental, polyphonic music is a difficult challenge which is yet far from being solved. Successful instrument recognition techniques in solos (monophonic or polyphonic recordings of single instruments) can help to deal with this task. We introduce an instrument recognition process in solo recordings of a set of instruments (bassoon, clarinet, flute, guitar, piano, cello and violin), which yields a high recognition rate. A large and very diverse solo database (108 different solos, all by different performers) is used in order to encompass the different sound possibilities of each instrument and evaluate the generalization abilities of the classification process. First we bring classification results using a very extensive collection of features (62 different feature types), and then use our GDE feature selection algorithm to select a smaller feature set with a relatively short computation time, which allows us to perform instrument reco...

The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR me... more The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR means, intuitively speaking, that given a musical recording, the computer attempts to identify which parts of the music are performed by which musical instruments. AMIR research has gained popularity over the last 10 years especially due to its applicability as a component inside "Intelligent" music search-engines, which can allow searching the Internet or mass-storage devices in personal "MP3" players for music using "intelligent" criteria such as musical style or composition - as opposed to searches involving only textual information provided with the musical files. Other usages of AMIR include integration and improvement of other Musical Information Retrieval tasks such as Automatic Transcription and Score Alignment, and as a tool in applications for composers and recording studios. AMIR is a compound process involving many challenging stages. The various s...

The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR me... more The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR means, intuitively speaking, that given a musical recording, the computer attempts to identify which parts of the music are performed by which musical instruments. AMIR research has gained popularity over the last 10 years especially due to its applicability as a component inside “Intelligent” music search-engines, which can allow searching the Internet or mass-storage devices in personal “MP3” players for music using “intelligent” criteria such as musical style or composition - as opposed to searches involving only textual information provided with the musical files. Other usages of AMIR include integration and improvement of other Musical Information Retrieval tasks such as Automatic Transcription and Score Alignment, and as a tool in applications for composers and recording studios. AMIR is a compound process involving many challenging stages. The various stages of the AMIR process as p...

Some initial works have appeared that began to deal with the complicated task of musical instrume... more Some initial works have appeared that began to deal with the complicated task of musical instrument recognition in multi-instrumental music. Although quite a few papers have already appeared on instrument recognition of singleinstrument musical phrases (“solos”), the work on solo recognition is not yet exhausted. The knowledge of how to deal well with solos can also help in recognition of multiinstrumental music. We present a process for recognition of a set of instruments (bassoon, clarinet, flute, guitar, piano, cello and violin) in solo recordings, which yields a high recognition rate. Among the points that distinguish our work are a large and very diverse solo database – 108 different solos, all by different performers, which apparently supplies a good generalization of the sound possibilities of each instrument, and a large collection of features – 62 different feature types. Using our GDE feature selection algorithm we minimize the feature set and present the 20 features which...

Journal of The Audio Engineering Society, 2006

In different papers dealing with automatic musical instrument recognition of pitched instruments,... more In different papers dealing with automatic musical instrument recognition of pitched instruments, the features used for classification are based solely on the fundamental frequencies and the harmonic series, ignoring the nonharmonic residual. In this paper we explore whether instrument recognition rate of pitched instruments is decreased by removing the non-harmonic information present in the sound signal.

Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the... more Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the nonharmonic Residual. It is common to treat the Harmonic Series as the main characteristic of the timbre of pitched musical instruments. But does the Harmonic Series indeed contain the complete information required for discriminating among different musical instruments? Could the non-harmonic Residual, the "noise", be used all by itself for instrument recognition? The paper begins by performing musical instrument recognition with an extensive sound collection using a large set of feature descriptors, achieving a high instrument recognition rate. Next, using Additive Analysis/Synthesis, each sound sample is resynthesized using solely its Harmonic Series. These "Harmonic" samples are then subtracted from the original samples to retrieve the non-harmonic Residuals. Instrument recognition is performed on the resynthesized and the "Residual" sound sets. The paper shows that the Harmonic Series by itself is indeed enough for achieving a high instrument recognition rate; however, the nonharmonic Residuals by themselves can also be used for distinguishing among musical instruments, although with lesser success. Using feature selection, the best 10 feature descriptors for instrument recognition out of our extensive feature set are presented for the Original, Harmonic and Residual sound sets.

HAL (Le Centre pour la Communication Scientifique Directe), 2009

Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the... more Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the nonharmonic Residual. It is common to treat the Harmonic Series as the main characteristic of the timbre of pitched musical instruments. But does the Harmonic Series indeed contain the complete information required for discriminating among different musical instruments? Could the non-harmonic Residual, the “noise”, be used all by itself for instrument recognition? The paper begins by performing musical instrument recognition with an extensive sound collection using a large set of feature descriptors, achieving a high instrument recognition rate. Next, using Additive Analysis/Synthesis, each sound sample is resynthesized using solely its Harmonic Series. These “Harmonic” samples are then subtracted from the original samples to retrieve the non-harmonic Residuals. Instrument recognition is performed on the resynthesized and the “Residual” sound sets. The paper shows that the Harmonic Seri...

The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR me... more The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR means, intuitively speaking, that given a musical recording, the computer attempts to identify which parts of the music are performed by which musical instruments. AMIR research has gained popularity over the last 10 years especially due to its applicability as a component inside “Intelligent” music search-engines, which can allow searching the Internet or mass-storage devices in personal “MP3” players for music using “intelligent” criteria such as musical style or composition - as opposed to searches involving only textual information provided with the musical files. Other usages of AMIR include integration and improvement of other Musical Information Retrieval tasks such as Automatic Transcription and Score Alignment, and as a tool in applications for composers and recording studios. AMIR is a compound process involving many challenging stages. The various stages of the AMIR process as p...

Journal of The Audio Engineering Society, 2006

Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the... more Sound produced by Musical instruments with definite pitch consists of the Harmonic Series and the nonharmonic Residual. It is common to treat the Harmonic Series as the main characteristic of the timbre of pitched musical instruments. But does the Harmonic Series indeed contain the complete information required for discriminating among different musical instruments? Could the non-harmonic Residual, the "noise", be used all by itself for instrument recognition? The paper begins by performing musical instrument recognition with an extensive sound collection using a large set of feature descriptors, achieving a high instrument recognition rate. Next, using Additive Analysis/Synthesis, each sound sample is resynthesized using solely its Harmonic Series. These "Harmonic" samples are then subtracted from the original samples to retrieve the non-harmonic Residuals. Instrument recognition is performed on the resynthesized and the "Residual" sound sets. The paper shows that the Harmonic Series by itself is indeed enough for achieving a high instrument recognition rate; however, the nonharmonic Residuals by themselves can also be used for distinguishing among musical instruments, although with lesser success. Using feature selection, the best 10 feature descriptors for instrument recognition out of our extensive feature set are presented for the Original, Harmonic and Residual sound sets.