van Dalen, R.C., Ragni, A. orcid.org/0000-0003-0634-4456 and Gales, M.J.F. (2013) Efficient decoding with generative score-spaces using the expectation semiring. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 26-31 May 2013, Vancouver, BC, Canada. IEEE , pp. 7619-7623. ISBN 9781479903566
Abstract
State-of-the-art speech recognisers are usually based on hidden Markov models (HMMs). They model a hidden symbol sequence with a Markov process, with the observations independent given that sequence. These assumptions yield efficient algorithms, but limit the power of the model. An alternative model that allows a wide range of features, including word- and phone-level features, is a log-linear model. To handle, for example, word-level variable-length features, the original feature vectors must be segmented into words. Thus, decoding must find the optimal combination of segmentation of the utterance into words and word sequence. Features must therefore be extracted for each possible segment of audio. For many types of features, this becomes slow. In this paper, long-span features are derived from the likelihoods of word HMMs. Derivatives of the log-likelihoods, which break the Markov assumption, are appended. Previously, decoding with this model took cubic time in the length of the sequence, and longer for higher-order derivatives. This paper shows how to decode in quadratic time.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2013 IEEE. |
Keywords: | Speech recognition; log-linear models; weighted finite-state transducers; expectation semiring |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Nov 2019 11:13 |
Last Modified: | 15 Nov 2019 11:13 |
Published Version: | https://ieeexplore.ieee.org/abstract/document/6639... |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/ICASSP.2013.6639145 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152846 |