research-article

A Maximum Likelihood Approach to Continuous Speech Recognition

Authors:

Lalit R. Bahl,

Frederick Jelinek,

Robert L. MercerAuthors Info & Claims

IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 5, Issue 2

Pages 179 - 190

https://doi.org/10.1109/TPAMI.1983.4767370

Published: 01 February 1983 Publication History

Abstract

Speech recognition is formulated as a problem of maximum likelihood decoding. This formulation requires statistical models of the speech production process. In this paper, we describe a number of statistical models for use in speech recognition. We give special attention to determining the parameters for such models from sparse data. We also describe two decoding methods, one appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks. To illustrate the usefulness of the methods described, we review a number of decoding results that have been obtained with them.

Cited By

View all

Sikosana MAjao OMaudsley-Barton S(2024)A Comparative Study of Hybrid Models in Health Misinformation Text ClassificationProceedings of the 4th International Workshop on Open Challenges in Online Social Networks10.1145/3677117.3685007(18-25)Online publication date: 10-Sep-2024
https://dl.acm.org/doi/10.1145/3677117.3685007
Calle PShao RLiu YHébert EKendzor DNeil JBusinelle MPan C(2024)Towards AI-Driven Healthcare: Systematic Optimization, Linguistic Analysis, and Clinicians’ Evaluation of Large Language Models for Smoking Cessation InterventionsProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641965(1-16)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3641965
Anagnostidis SPavllo DBiggio LNoci LLucchi AHofmann TOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Dynamic context pruning for efficient and interpretable autoregressive transformersProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668967(65202-65223)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668967
Show More Cited By

A Maximum Likelihood Approach to Continuous Speech Recognition
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing

Recommendations

A noise-robust speech recognition approach incorporating normalized speech/non-speech likelihood into hypothesis scores

In noisy environments, speech recognition decoders often incorrectly produce speech hypotheses for non-speech periods, and non-speech hypotheses, such as silence or a short pause, for speech periods. It is crucial to reduce such errors to improve the ...
Regularized minimum variance distortionless response-based cepstral features for robust continuous speech recognition

We study the low-variance and robust features for speech recognition system on the AURORA-4 corpus.We propose to compute cepstral features from a regularized MVDR (RMVDR) spectral estimates, denoted as RMVDR-based Cepstral Coefficient (RMCC) features.A ...
Using tone information in Cantonese continuous speech recognition

In Chinese languages, tones carry important information at various linguistic levels. This research is based on the belief that tone information, if acquired accurately and utilized effectively, contributes to the automatic speech recognition of ...

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Pattern Analysis and Machine Intelligence

IEEE Transactions on Pattern Analysis and Machine Intelligence Volume 5, Issue 2

February 1983

122 pages

ISSN:0162-8828

Issue’s Table of Contents

Publisher

IEEE Computer Society

United States

Publication History

Published: 01 February 1983

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

185
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Sikosana MAjao OMaudsley-Barton S(2024)A Comparative Study of Hybrid Models in Health Misinformation Text ClassificationProceedings of the 4th International Workshop on Open Challenges in Online Social Networks10.1145/3677117.3685007(18-25)Online publication date: 10-Sep-2024
https://dl.acm.org/doi/10.1145/3677117.3685007
Calle PShao RLiu YHébert EKendzor DNeil JBusinelle MPan C(2024)Towards AI-Driven Healthcare: Systematic Optimization, Linguistic Analysis, and Clinicians’ Evaluation of Large Language Models for Smoking Cessation InterventionsProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641965(1-16)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3641965
Anagnostidis SPavllo DBiggio LNoci LLucchi AHofmann TOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Dynamic context pruning for efficient and interpretable autoregressive transformersProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668967(65202-65223)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668967
Hassid MRemez TNguyen TGat IConneau AKreuk FCopet JDefossez ASynnaeve GDupoux ESchwartz RAdi YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Textually pretrained speech language modelsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668893(63483-63501)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668893
Gupta DChow YTulepbergenov AGhavamzadeh MBoutilier COh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Offline reinforcement learning for mixture-of-expert dialogue managementProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666381(5912-5935)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666381
Lo PLim E(2023)Non-monotonic Generation of Knowledge Paths for Context UnderstandingACM Transactions on Management Information Systems10.1145/362799415:1(1-28)Online publication date: 20-Oct-2023
https://dl.acm.org/doi/10.1145/3627994
Wang YLin JYu ZHu WKarlsson B(2023)Open-world story generation with structured knowledge enhancementNeurocomputing10.1016/j.neucom.2023.126792559:COnline publication date: 28-Nov-2023
https://dl.acm.org/doi/10.1016/j.neucom.2023.126792
Noya EBenedí JSánchez JAnitei D(2023)Discriminative estimation of probabilistic context-free grammars for mathematical expression recognition and retrievalPattern Analysis & Applications10.1007/s10044-023-01158-826:4(1571-1584)Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.1007/s10044-023-01158-8
Ho NNguyen DGustafson JWong W(2023)Bedot: Bit Efficient Dot Product for Deep Generative ModelsNext Generation Arithmetic10.1007/978-3-031-32180-1_2(19-37)Online publication date: 1-Mar-2023
https://dl.acm.org/doi/10.1007/978-3-031-32180-1_2
Balli CGuzel MBostanci EMishra A(2022)Sentimental Analysis of Twitter Users from Turkish Content with Natural Language ProcessingComputational Intelligence and Neuroscience10.1155/2022/24551602022Online publication date: 1-Jan-2022
https://dl.acm.org/doi/10.1155/2022/2455160
Show More Cited By

Abstract

Cited By

Recommendations

A noise-robust speech recognition approach incorporating normalized speech/non-speech likelihood into hypothesis scores

Regularized minimum variance distortionless response-based cepstral features for robust continuous speech recognition

Using tone information in Cantonese continuous speech recognition

Comments

Information

Published In

Publisher

Publication History

Author Tags

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Share

Share this Publication link

Share on social media

Affiliations