The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Semi-tied covariance matrices for hidden Markov models
Abstract
There is normally a simple choice made in the form of the covariance matrix to be used with continuous-density HMMs. Either a diagonal covariance matrix is used, with the underlying assumption that elements of the feature vector are independent, or a full or block-diagonal matrix is used, where all or some of the correlations are explicitly modeled. Unfortunately when using full or block-diagonal covariance matrices there tends to be a dramatic increase in the number of parameters per Gaussian component, limiting the number of components which may be robustly estimated. This paper introduces a new form of covariance matrix which allows a few "full" covariance matrices to be shared over many distributions, whilst each distribution maintains its own "diagonal" covariance matrix. In contrast to other schemes which have hypothesized a similar form, this technique fits within the standard maximum-likelihood criterion used for training HMMs. The new form of covariance matrix is evaluated on a large-vocabulary speech-recognition task. In initial experiments the performance of the standard system was achieved using approximately half the number of parameters. Moreover, a 10% reduction in word error rate compared to a standard system can be achieved with less than a 1% increase in the number of parameters and little increase in recognition time.
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
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743
Introduction to Statistical Pattern Recognition
(1990) · Elsevier eBooks · doi:10.1016/c2009-0-27872-x · Cited by 11,031
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465 · cited 1×
“The use of the discrete cosine transform (DCT) in speech recognition is common for this reason [ 3 ].”
Maximum likelihood estimation from incomplete data via the EM algorithm
Dempster, A. P. (1977) · Journal of the Royal Statistical Society Series A (Statistics in Society) · Cited by 4,543
Maximum Likelihood from Incomplete Data via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1976) · Cited by 4,517
Leggetter, C. J., & Woodland, P. C. (1995) · Computer Speech & Language · doi:10.1006/csla.1995.0010 · Cited by 2,192
Maximum likelihood linear transformations for HMM-based speech recognition
Gales, M. J. F. (1998) · Computer Speech & Language · doi:10.1006/csla.1998.0043 · Cited by 1,482
Self-citationTree-based state tying for high accuracy acoustic modelling
Young, S. J., Odell, J. J., & Woodland, P. C. (1994) · Proceedings of the workshop on Human Language Technology - HLT '94 · doi:10.3115/1075812.1075885 · Cited by 664
Mean and variance adaptation within the MLLR framework
Gales, M. J. F., & Woodland, P. C. (1996) · Computer Speech & Language · doi:10.1006/csla.1996.0013 · Cited by 393
Self-citation
Cited by
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Kaldi Speech Recognition Toolkit
Povey, D. (2024) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.57702/jb3fvbn9 · Cited by 4,609
Statistical parametric speech synthesis
Zen, H., Tokuda, K., & Black, A. W. (2009) · Speech Communication · doi:10.1016/j.specom.2009.04.004 · Cited by 1,195
Japanese and Korean voice search
Schuster, M., & Nakajima, K. (2012) · 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2012.6289079 · Cited by 862
Sequence-discriminative training of deep neural networks
Veselý, K., Ghoshal, A., Burget, L., & Povey, D. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-548 · Cited by 657
The Application of Hidden Markov Models in Speech Recognition
Gales, M., & Young, S. (2007) · now publishers, Inc. eBooks · doi:10.1561/9781601981219 · Cited by 557
Self-citationAutomatic speech recognition and speech variability: A review
Benzeghiba, M., De Mori, R., Deroo, O., Dupont, S., Erbes, T., Jouvet, D., Fissore, L., Laface, P., Mertins, A., Ris, C., et al. (2007) · Speech Communication · doi:10.1016/j.specom.2007.02.006 · Cited by 529
Deep Convolutional Neural Networks for Large-scale Speech Tasks
Sainath, T. N., Kingsbury, B., Saon, G., Soltau, H., Mohamed, A.-R., Dahl, G., & Ramabhadran, B. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.08.005 · Cited by 496
The Application of Hidden Markov Models in Speech Recognition
Gales, M., & Young, S. (2007) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000004 · Cited by 496
Self-citationEigenvoice modeling with sparse training data
Kenny, P., Boulianne, G., & Dumouchel, P. (2005) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/tsa.2004.840940 · Cited by 475
A tutorial on task-parameterized movement learning and retrieval
Calinon, S. (2016) · Intelligent Service Robotics · doi:10.1007/s11370-015-0187-9 · Cited by 422
Data Augmentation for Deep Neural Network Acoustic Modeling
Cui, X., Goel, V., & Kingsbury, B. (2015) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2015.2438544 · Cited by 376
Yamagishi, J., Kobayashi, T., Nakano, Y., Ogata, K., & Isogai, J. (2009) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2008.2006647 · Cited by 324
The subspace Gaussian mixture model—A structured model for speech recognition
Povey, D., Burget, L., Agarwal, M., Akyazi, P., Kai, F., Ghoshal, A., Glembek, O., Goel, N., Karafiát, M., Rastrow, A., et al. (2011) · Computer Speech & Language · doi:10.1016/j.csl.2010.06.003 · Cited by 276
Convolutional Neural Networks for Distant Speech Recognition
Swietojanski, P., Ghoshal, A., & Renals, S. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2325781 · Cited by 253
Unlimited vocabulary speech recognition with morph language models applied to Finnish
Hirsimäki, T., Creutz, M., Siivola, V., Kurimo, M., Virpioja, S., & Pylkkönen, J. (2006) · Computer Speech & Language · doi:10.1016/j.csl.2005.07.002 · Cited by 124
Learning Robot Manipulation Tasks With Task-Parameterized Semitied Hidden Semi-Markov Model
Tanwani, A. K., & Calinon, S. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2517825 · Cited by 84
New Era for Robust Speech Recognition
(2017) · doi:10.1007/978-3-319-64680-0 · Cited by 48
Automatic detection of phonological errors in child speech using siamese recurrent autoencoder
Ng, S.-I., & Lee, T. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2145 · Cited by 14
Metadata
- Authors
- Gales, M. J. F.
- Venue
- IEEE Transactions on Speech and Audio Processing
- Published
- 1999-05
- Volume
- 7
- Issue
- 3
- Pages
- 272-281
- ISSN
- 1063-6676 (ISSN-L)
- OpenAlex
- W2106554350
- Cited by
- 537
- References
- 13
- FWCI
- 12.61
- 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.