Unsupervised Pattern Discovery in Speech
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to classify speech into categories defined by a prespecified inventory of lexical units (i.e., phones or words). Instead, we attempt to discover such an inventory in an unsupervised manner by exploiting the structure of repeating patterns within the speech signal. We show how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream. Our approach to unsupervised word acquisition utilizes a segmental variant of a widely used dynamic programming technique, which allows us to find matching acoustic patterns between spoken utterances. By aggregating information about these matching patterns across audio streams, we demonstrate how to group similar acoustic sequences together to form clusters corresponding to lexical entities such as words and short multiword phrases. On a corpus of academic lecture material, we demonstrate that clusters found using this technique exhibit high purity and that many of the corresponding lexical identities are relevant to the underlying audio stream.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Normalized cuts and image segmentation
Shi, J., & Malik, J. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868688 · Cited by 15,502
Finding and evaluating community structure in networks
Newman, M. E. J., & Girvan, M. (2004) · Physical Review E · doi:10.1103/physreve.69.026113 · Cited by 13,931 · cited 1×
“In contrast to simple edge thresholding, a number of more sophisticated algorithms for automatic graph clustering have been proposed by researchers in other fields [32], [33].”
Needleman, S. B., & Wunsch, C. D. (1970) · Journal of Molecular Biology · doi:10.1016/0022-2836(70)90057-4 · Cited by 11,288 · cited 1×
“In particular, a popular approach to alignment is the use of dynamic programming to search an edit distance matrix (also known as a distance matrix,positionweightmatrix,orposition-specific scoring matrix) for optimal global alignments [8] or optimal local alignments [9].”
Term-weighting approaches in automatic text retrieval
Salton, G., & Buckley, C. (1988) · Information Processing & Management · doi:10.1016/0306-4573(88)90021-0 · Cited by 9,740
Advances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.001.0001 · Cited by 8,890
On Spectral Clustering: Analysis and an algorithm
Ng, A. Y., Jordan, M. I., & Weiss, Y. (2001) · Cited by 8,159
Dynamic Programming Algorithm Optimization for Spoken Word Recognition
Sakoe, H., & Chiba, S. (1978) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/tassp.1978.1163055 · Cited by 6,727
Statistical learning by 8-month-old infants
Saffran, J. R., Aslin, R. N., & Newport, E. L. (1996) · Science · doi:10.1126/science.274.5294.1926 · Cited by 5,659
Fast algorithm for detecting community structure in networks
Newman, M. E. J. (2004) · Physical Review E · doi:10.1103/physreve.69.066133 · Cited by 5,406
Biological sequence analysis probabilistic models of proteins and nucleic acids
Durbin, R. M., Eddy, S. R., Krogh, A., & Mitchison, G. (1998) · Cited by 3,565
Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids
Durbin, R., Eddy, S. R., Krogh, A., & Mitchison, G. (1998) · Cambridge University Press eBooks · doi:10.1017/cbo9780511790492 · Cited by 3,246
FREQUENCY ANALYSIS OF ENGLISH USAGE: LEXICON AND GRAMMAR
Francis, W. N., Kučera, H., & Mackie, A. W. (1983) · Medical Entomology and Zoology · Cited by 2,310
Combinatorial pattern discovery in biological sequences: The TEIRESIAS algorithm.
Rigoutsos, I., & Floratos, A. (1998) · Bioinformatics · doi:10.1093/bioinformatics/14.1.55 · Cited by 557
Learning words from sights and sounds: A computational model
Roy, D. K., & Pentland, A. P. (2002) · Cognitive Science · doi:10.1207/s15516709cog2601_4 · Cited by 521
The LIMSI Broadcast News transcription system
Gauvain, J., Lamel, L. F., & Adda, G. (2002) · Speech Communication · doi:10.1016/s0167-6393(01)00061-9 · Cited by 433
A Spectral Clustering Approach To Finding Communities in Graphs
White, S., & Smyth, P. (2005) · Proceedings of the 2005 SIAM International Conference on Data Mining · doi:10.1137/1.9781611972757.25 · Cited by 404
Learning Segmentation by Random Walks
Meilă, M., & Shi, J. (2000) · neural information processing systems · Cited by 365
An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery
Brent, M. R. (1999) · Machine Learning · doi:10.1023/a:1007541817488 · Cited by 351
Contextual dependencies in unsupervised word segmentation
Goldwater, S., Griffiths, T. L., & Johnson, M. (2006) · Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06 · doi:10.3115/1220175.1220260 · Cited by 305
Approaches to the Automatic Discovery of Patterns in Biosequences
BRAZMA, A., JONASSEN, I., EIDHAMMER, I., & GILBERT, D. (1998) · Journal of Computational Biology · doi:10.1089/cmb.1998.5.279 · Cited by 303
A new algorithm for best subsequence alignments with application to tRNA-rRNA comparisons
Waterman, M. S., & Eggert, M. (1987) · Journal of Molecular Biology · doi:10.1016/0022-2836(87)90478-5 · Cited by 292
A probabilistic framework for segment-based speech recognition
Glass, J. R. (2003) · Computer Speech & Language · doi:10.1016/s0885-2308(03)00006-8 · Cited by 280
Self-citationA level building dynamic time warping algorithm for connected word recognition
Myers, C., & Rabiner, L. (1981) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1981.1163527 · Cited by 261
A survey of motif discovery methods in an integrated framework.
Sandve, G. K., & Drabløs, F. (2006) · Biology Direct · doi:10.1186/1745-6150-1-11 · Cited by 172
Unsupervised Language Acquisition
de Marcken, C. (1996) · arXiv (Cornell University) · doi:10.48550/arxiv.cmp-lg/9611002 · Cited by 126
A Statistical Model for Word Discovery in Transcribed Speech
Venkataraman, A. (2001) · Computational Linguistics · doi:10.1162/089120101317066113 · Cited by 120
Lin, Y.-L., Jiang, T., & Chao, K. (2002) · Journal of Computer and System Sciences · doi:10.1016/s0022-0000(02)00010-7 · Cited by 105
Unsupervised pattern discovery in speech: applications to word acquisition and speaker segmentation
Glass, J. R., & Park, A. S. (2007) · Cited by 12
Self-citation
Cited by
Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams
Zhang, Y., & Glass, J. R. (2009) · 2009 IEEE Workshop on Automatic Speech Recognition & Understanding · doi:10.1109/asru.2009.5372931 · Cited by 327
Self-citationUnsupervised speech representation learning using WaveNet autoencoders
Chorowski, J., Weiss, R. J., Bengio, S., & van den Oord, A. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2938863 · Cited by 325
“Linguistic unit discovery models detect recurring speech patterns at a word-like level, finding commonly repeated segments with a constrained dynamic time warping [74].”
BackgroundDynamic Development in Speaking Versus Writing in Identical Twins
Chan, H., Verspoor, M., & Vahtrick, L. (2015) · Language Learning · doi:10.1111/lang.12107 · Cited by 68
Word Segmentation on Discovered Phone Units With Dynamic Programming and Self-Supervised Scoring
Kamper, H. (2023) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2022.3229264 · Cited by 24
“One approach would be to incorporate top-down information from a sparse term discovery system tailored towards discovering recurring but longer words [55], [56], [59], which could be used to bootstrap segmentation.”
Background
Metadata
- Authors
- Park, A. S., & Glass, J. R.
- Venue
- IEEE Transactions on Audio, Speech, and Language Processing
- Published
- 2008-01
- Volume
- 16
- Issue
- 1
- Pages
- 186-197
- ISSN
- 1558-7916 (ISSN-L)
- OpenAlex
- W2114347655
- Cited by
- 351
- References
- 28
- FWCI
- 9.46
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.