CoChat
Sign Up
Cited by 203Speech Recognition and SynthesisSpeech and Audio ProcessingPhonetics and Phonology Research

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Global optimization of a neural network-hidden Markov model hybrid

Bengio, Y., De Mori, R., Flammia, G., Kompe, R.·1992·IEEE Transactions on Neural Networks
DOI 10.1109/72.125866
Open this paper in CoChat — free account

Abstract

The integration of multilayered and recurrent artificial neural networks (ANNs) with hidden Markov models (HMMs) is addressed. ANNs are suitable for approximating functions that compute new acoustic parameters, whereas HMMs have been proven successful at modeling the temporal structure of the speech signal. In the approach described, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters. Results on speaker-independent recognition experiments using this integrated ANN-HMM system on the TIMIT continuous speech database are reported.

Overview

Integrity signals

Registry

Crossref · 10.1109/72.125866

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Flagged first, then by citations

Show all 1 references

Research works printed but not linked: 30

  1. steward, 1973, Introduction to Matrix Computations
  2. 10.1109/ICASSP.1990.115733 · DOI
  3. 10.1109/ICASSP.1990.115720 · DOI
  4. 10.1109/ICASSP.1990.115724 · DOI
  5. 10.1109/ICASSP.1990.115848 · DOI
  6. 10.1109/29.45543 · DOI
  7. bridle, 1990, Advances in Neural Information Processing Systems 2, 211
  8. 10.1109/ICASSP.1990.115740 · DOI
  9. 10.1016/0167-6393(90)90010-7 · DOI
  10. 10.1214/aoms/1177697196 · DOI
  11. 10.1109/5.18626 · DOI · Paper page
  12. le cun, 1989, Connectionism in Perspective, 143
  13. 10.1145/63342.63345 · DOI
  14. 10.1016/0893-6080(90)90028-J · DOI
  15. rumelhart, 1986, Parallel Distributed Processing, 1, 318
  16. 10.1016/0167-6393(90)90041-7 · DOI
  17. bridle, 1991, Advances in Neural Information Processing Systems 3
  18. 10.1162/neco.1989.1.1.1 · DOI
  19. 10.1109/ICASSP.1990.115768 · DOI
  20. robinson, 1990, Phoneme recognition from the TIMIT database using recurrent error propagation networks
  21. 10.1109/29.46546 · DOI
  22. bourlard, 1988, Advances in neural information processing systems, 1, 502
  23. 10.1109/TASSP.1985.1164586 · DOI
  24. 10.1109/29.90371 · DOI
  25. bengio, 1990, Advances in Neural Information Processing Systems 2, 218
  26. bengio, 1991, Artificial neural networks and their application to sequence recognition
  27. stevens, 1981, Perspectives on the Study of Speech, 1
  28. o'shaughnessy, 1987, Speech CommunicationHuman and Machine
  29. 10.1016/0167-6393(92)90020-8 · DOI
  30. 10.1016/B978-0-12-248550-3.50023-4 · DOI

Cited by

Sorted by citations

See all 203

Metadata

Authors
Bengio, Y., De Mori, R., Flammia, G., & Kompe, R.
Affiliations
  • McGill University (CA)
  • Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
ORCID
Bengio, Y.
Venue
IEEE Transactions on Neural Networks
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
1992-03
Volume
3
Issue
2
Pages
252-259
ISSN
1045-9227 (ISSN-L)
DOI
10.1109/72.125866
OpenAlex
W2148099973
Cited by
203
References
1
Citations by year
2026: 2 · 2025: 3 · 2024: 1 · 2023: 6 · 2022: 4 · 2021: 6 · 2020: 3 · 2019: 4 · 2018: 4 · 2017: 4 · 2016: 12 · 2015: 7 · 2014: 7 · 2013: 2 · 2012: 7
FWCI
10.11
Type
journal article
Language
en
Open access
closed
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)
Locations
  • IEEE Transactions on Neural Networks (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
Keywords
global optimization, recurrent neural networks, hidden Markov models, acoustic parameter estimation, speech recognition, speaker-independent recognition, TIMIT database, connected speech

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