The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Boosted MMI for model and feature-space discriminative training
Abstract
We present a modified form of the maximum mutual information (MMI) objective function which gives improved results for discriminative training. The modification consists of boosting the likelihoods of paths in the denominator lattice that have a higher phone error relative to the correct transcript, by using the same phone accuracy function that is used in Minimum Phone Error (MPE) training. We combine this with another improvement to our implementation of the Extended Baum-Welch update equations for MMI, namely the canceling of any shared part of the numerator and denominator statistics on each frame (a procedure that is already done in MPE). This change affects the Gaussian-specific learning rate. We also investigate another modification whereby we replace I-smoothing to the ML estimate with I-smoothing to the previous iteration's value. Boosted MMI gives better results than MPE in both model and feature-space discriminative training, although not consistently.
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 mutual information estimation of hidden Markov model parameters for speech recognition
Bahl, L., Brown, P., de Souza, P., & Mercer, R. (2005) · ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1986.1169179 · Cited by 817 · cited 1×
“The Maximum Mutual Information (MMI) objective function [3, 4, 5] seeks to maximize the posterior probability of the correct utter-”
BackgroundMinimum Phone Error and I-smoothing for improved discriminative training
Povey, D., & Woodland, P. C. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2002.5743665 · Cited by 622
Self-citationLarge Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition
Sha, F., & Saul, L. K. (2006) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2006.1660008 · Cited by 123
Sha, F., & Saul, L. K. (2007) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2007.366912 · Cited by 74
Evaluation of Proposed Modifications to MPE for Large Scale Discriminative Training
Povey, D., & Kingsbury, B. E. D. (2007) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2007.366914 · Cited by 73
Self-citationImprovements to fMPE for discriminative training of features
Povey, D. (2005) · Interspeech (USB) · doi:10.21437/interspeech.2005-133 · Cited by 47
Self-citationImproved discriminative training techniques for large vocabulary continuous speech recognition
Povey, D., & Woodland, P. C. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2001.940763 · Cited by 47
Self-citation
Cited by
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Self-citation“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
Self-citationContext-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011
“Recently, discriminative training strategies such as MMI [5], MCE [6], [7], MPE [8], [9], and large-margin techniques [10]–[17] have been proposed.”
BackgroundA time delay neural network architecture for efficient modeling of long temporal contexts
Peddinti, V., Povey, D., & Khudanpur, S. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-647 · Cited by 986
“However, speaker adaptation techniques like fMLLR [4] require two passes of decoding.”
MethodSelf-citationJapanese 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
Metadata
- Authors
- Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., & Visweswariah, K.
- Venue
- 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
- Publisher
- IEEE
- Published
- 2008-03
- Pages
- 4057-4060
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2125234026
- Cited by
- 341
- References
- 7
- FWCI
- 24.31
- Type
- conference paper
- 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.