{"title":"学习复调音频与乐谱对齐的最佳功能","authors":"C. Joder, S. Essid, G. Richard","doi":"10.1109/TASL.2013.2266794","DOIUrl":null,"url":null,"abstract":"This paper addresses the design of feature functions for the matching of a musical recording to the symbolic representation of the piece (the score). These feature functions are defined as dissimilarity measures between the audio observations and template vectors corresponding to the score. By expressing the template construction as a linear mapping from the symbolic to the audio representation, one can learn the feature functions by optimizing the linear transformation. In this paper, we explore two different learning strategies. The first one uses a best-fit criterion (minimum divergence), while the second one exploits a discriminative framework based on a Conditional Random Fields model (maximum likelihood criterion). We evaluate the influence of the feature functions in an audio-to-score alignment task, on a large database of popular and classical polyphonic music. The results show that with several types of models, using different temporal constraints, the learned mappings have the potential to outperform the classic heuristic mappings. Several representations of the audio observations, along with several distance functions are compared in this alignment task. Our experiments elect the symmetric Kullback-Leibler divergence. Moreover, both the spectrogram and a CQT-based representation turn out to provide very accurate alignments, detecting more than 97% of the onsets with a precision of 100 ms with our most complex system.","PeriodicalId":55014,"journal":{"name":"IEEE Transactions on Audio Speech and Language Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TASL.2013.2266794","citationCount":"30","resultStr":"{\"title\":\"Learning Optimal Features for Polyphonic Audio-to-Score Alignment\",\"authors\":\"C. Joder, S. Essid, G. Richard\",\"doi\":\"10.1109/TASL.2013.2266794\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper addresses the design of feature functions for the matching of a musical recording to the symbolic representation of the piece (the score). These feature functions are defined as dissimilarity measures between the audio observations and template vectors corresponding to the score. By expressing the template construction as a linear mapping from the symbolic to the audio representation, one can learn the feature functions by optimizing the linear transformation. In this paper, we explore two different learning strategies. The first one uses a best-fit criterion (minimum divergence), while the second one exploits a discriminative framework based on a Conditional Random Fields model (maximum likelihood criterion). We evaluate the influence of the feature functions in an audio-to-score alignment task, on a large database of popular and classical polyphonic music. The results show that with several types of models, using different temporal constraints, the learned mappings have the potential to outperform the classic heuristic mappings. Several representations of the audio observations, along with several distance functions are compared in this alignment task. Our experiments elect the symmetric Kullback-Leibler divergence. Moreover, both the spectrogram and a CQT-based representation turn out to provide very accurate alignments, detecting more than 97% of the onsets with a precision of 100 ms with our most complex system.\",\"PeriodicalId\":55014,\"journal\":{\"name\":\"IEEE Transactions on Audio Speech and Language Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1109/TASL.2013.2266794\",\"citationCount\":\"30\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Audio Speech and Language Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TASL.2013.2266794\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Audio Speech and Language Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TASL.2013.2266794","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Learning Optimal Features for Polyphonic Audio-to-Score Alignment
This paper addresses the design of feature functions for the matching of a musical recording to the symbolic representation of the piece (the score). These feature functions are defined as dissimilarity measures between the audio observations and template vectors corresponding to the score. By expressing the template construction as a linear mapping from the symbolic to the audio representation, one can learn the feature functions by optimizing the linear transformation. In this paper, we explore two different learning strategies. The first one uses a best-fit criterion (minimum divergence), while the second one exploits a discriminative framework based on a Conditional Random Fields model (maximum likelihood criterion). We evaluate the influence of the feature functions in an audio-to-score alignment task, on a large database of popular and classical polyphonic music. The results show that with several types of models, using different temporal constraints, the learned mappings have the potential to outperform the classic heuristic mappings. Several representations of the audio observations, along with several distance functions are compared in this alignment task. Our experiments elect the symmetric Kullback-Leibler divergence. Moreover, both the spectrogram and a CQT-based representation turn out to provide very accurate alignments, detecting more than 97% of the onsets with a precision of 100 ms with our most complex system.
期刊介绍:
The IEEE Transactions on Audio, Speech and Language Processing covers the sciences, technologies and applications relating to the analysis, coding, enhancement, recognition and synthesis of audio, music, speech and language. In particular, audio processing also covers auditory modeling, acoustic modeling and source separation. Speech processing also covers speech production and perception, adaptation, lexical modeling and speaker recognition. Language processing also covers spoken language understanding, translation, summarization, mining, general language modeling, as well as spoken dialog systems.