Machine Learning Paradigms for Speech Recognition: An Overview
The DOI matches its Crossref record; 229 of the 229 references it cites were found in a registry or an index.
Abstract
Automatic Speech Recognition (ASR) has historically been a driving force behind many machine learning (ML) techniques, including the ubiquitously used hidden Markov model, discriminative learning, structured sequence learning, Bayesian learning, and adaptive learning. Moreover, ML can and occasionally does use ASR as a large-scale, realistic application to rigorously test the effectiveness of a given technique, and to inspire new problems arising from the inherently sequential and dynamic nature of speech. On the other hand, even though ASR is available commercially for some applications, it is largely an unsolved problem—for almost all applications, the performance of ASR is not on par with human performance. New insight from modern ML methodology shows great promise to advance the state-of-the-art in ASR technology. This overview article provides readers with an overview of modern ML techniques as utilized in the current and as relevant to future ASR research and systems. The intent is to foster further cross-pollination between the ML and ASR communities than has occurred in the past. The article is organized according to the major ML paradigms that are either popular already or have potential for making significant contributions to ASR technology. The paradigms presented and elaborated in this overview include: generative and discriminative learning; supervised, unsupervised, semi-supervised, and active learning; adaptive and multi-task learning; and Bayesian learning. These learning paradigms are motivated and discussed in the context of ASR technology and applications. We finally present and analyze recent developments of deep learning and learning with sparse representations, focusing on their direct relevance to advancing ASR technology.
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
Items 201–229 of 229
Detection-based ASR in the automatic speech attribute transcription project
Bromberg, I., Qian, Q., Hou, J., Li, J., Ma, C., Matthews, B. A., Moreno-Daniel, A., Morris, J., Siniscalchi, S. M., Tsao, Y., et al. (2007) · Interspeech (USB) · doi:10.21437/interspeech.2007-510 · Cited by 40
On the relations between modeling approaches for speech recognition
Ephraim, Y., & Rabiner, L. R. (1990) · IEEE Transactions on Information Theory · doi:10.1109/18.52483 · Cited by 38
A Bayesian Divergence Prior for Classiffier Adaptation
Li, X., & Bilmes, J. (2007) · International Conference on Artificial Intelligence and Statistics · Cited by 37
Self-citationDeep-structured hidden conditional random fields for phonetic recognition
Yu, D., & Deng, L. (2010) · Interspeech (USB) · doi:10.21437/interspeech.2010-35 · Cited by 36
Self-citationLarge-margin minimum classification error training: A theoretical risk minimization perspective
Yu, D., Deng, L., He, X., & Acero, A. (2008) · Computer Speech & Language · doi:10.1016/j.csl.2008.03.002 · Cited by 35
Self-citationEquivalence of Generative and Log-Linear Models
Heigold, G., Ney, H., Lehnen, P., Gass, T., & Schlüter, R. (2010) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2010.2082532 · Cited by 34
Dynamic Speech Models: Theory, Algorithms, and Applications
Deng, L. (2006) · Synthesis lectures on speech and audio processing · doi:10.1007/978-3-031-02555-6 · Cited by 34
Self-citationRao-Blackwellised Gibbs sampling for switching linear dynamical systems
Rosti, A.-V. I., & Gales, M. (2004) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2004.1326109 · Cited by 33
SCARF: a segmental conditional random field toolkit for speech recognition
Zweig, G., & Nguyen, P. (2010) · Interspeech (USB) · doi:10.21437/interspeech.2010-307 · Cited by 32
Bayesian Sensing Hidden Markov Models
Saon, G., & Chien, J. (2011) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2129911 · Cited by 30
Deng, L., Yu, D., & Acero, A. (2005) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tsa.2005.854107 · Cited by 28
Self-citationA multiple-level linear/linear segmental HMM with a formant-based intermediate layer
Russell, M. J., & Jackson, P. J. B. (2004) · Computer Speech & Language · doi:10.1016/j.csl.2004.08.001 · Cited by 26
Large vocabulary speech recognition using deep tensor neural networks
Yu, D., Deng, L., & Seide, F. T. B. (2012) · Interspeech (USB) · doi:10.21437/interspeech.2012-2 · Cited by 25
Self-citationAdaptation algorithms for large scale HMM recognizers
Zavaliagkos, G., Schwartz, R., McDonough, J. E., & Makhoul, J. I. (1995) · European Conference on Speech Communication and Technology (Eurospeech) · doi:10.21437/eurospeech.1995-283 · Cited by 25
Jeff, Z., & Deng, L. (2000) · Computer Speech & Language · doi:10.1006/csla.1999.0136 · Cited by 25
Self-citationUpdated MINDS Report on Speech Recognition and Understanding
Baker, J., Deng, L., Khudanpur, S. P., Lee, C.-H., Glass, J. R., & Morgan, N. (2009) · IEEE Signal Processing Magazine · Cited by 23
Self-citationStructured Discriminative Models For Speech Recognition: An Overview
Gales, M., Watanabe, S., & Fosler‐Lussier, E. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2207140 · Cited by 23
Discriminative semi-parametric trajectory model for speech recognition
Sim, K. C., & Gales, M. (2007) · Computer Speech & Language · doi:10.1016/j.csl.2007.03.004 · Cited by 23
Lee, L. J., Attias, H. T., & Deng, L. (2003) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2003.1198920 · Cited by 21
Self-citationParameter Estimation of Statistical Models Using Convex Optimization
Jiang, H., & Li, X. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.936018 · Cited by 19
Self-citationA novel decision function and the associated decision-feedback learning for speech translation
Zhang, Y., Deng, L., He, X., & Acero, A. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5947631 · Cited by 19
Self-citationCross-task knowledge-constrained self training
Daumé, H. (2008) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/1613715.1613800 · Cited by 18
Hidden conditional random field with distribution constraints for phone classification
Yu, D., Deng, L., & Acero, A. (2009) · Interspeech (USB) · doi:10.21437/interspeech.2009-235 · Cited by 18
Self-citationUse of incrementally regulated discriminative margins in MCE training for speech recognition
Yu, D., Deng, L., He, X., & Acero, A. (2006) · Interspeech (USB) · doi:10.21437/interspeech.2006-606 · Cited by 18
Self-citationDeng, L., Yu, D., & Acero, A. (2006) · Cited by 15
Self-citationMajor Advances and Emerging Developments of Graphical Models [From the Guest Editors]
Jordan, M. I., Sudderth, E. B., Wainwright, M. J., & Willsky, A. S. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.938115 · Cited by 14
On the use of virtual evidence in conditional random fields
Li, X. (2009) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/1699648.1699675 · Cited by 13
Self-citationA convex optimization method for joint mean and variance parameter estimation of large-margin CDHMM
Chang, T., Luo, Z.-Q. T., Deng, L., & Chi, C. (2008) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2008.4518544 · Cited by 12
Self-citationLiu, C., Hu, Y., Dai, L.-R., & Jiang, H. (2011) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2144969 · Cited by 3
Cited by
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480
“, Chapter 28 in [264], and Reference [95], it may be natural to just classify deep learning techniques into deep discriminative models (e.”
BackgroundSelf-citationDeep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076
1D convolutional neural networks and applications: A survey
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.107398 · Cited by 2,835
Convolutional Neural Networks for Speech Recognition
Abdel-Hamid, O., Mohamed, A.-R., Jiang, H., Deng, L., Penn, G., & Yu, D. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2339736 · Cited by 2,262
Self-citationBuilding End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
Serban, I., Sordoni, A., Bengio, Y., Courville, A., & Pineau, J. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.9883 · Cited by 1,615
Metadata
- Authors
- Deng, L., & Li, X.
- Venue
- IEEE Transactions on Audio, Speech, and Language Processing
- Published
- 2013-05
- Volume
- 21
- Issue
- 5
- Pages
- 1060-1089
- ISSN
- 1558-7916 (ISSN-L)
- 1558-7924
- OpenAlex
- W2161742217
- Cited by
- 456
- References
- 229
- FWCI
- 29.82
- 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.