Change search
ReferencesLink to record
Permanent link

Direct link
A fast HMM match algorithm for very large vocabulary speech recognition
KTH, Superseded Departments, Speech, Music and Hearing.
2004 (English)In: Speech Communication, ISSN 0167-6393, Vol. 42, no 2, 191-206 p.Article in journal (Refereed) Published
Abstract [en]

The search over context-dependent continuous density Hidden Markov Models (HMMs), including state-likelihood computations, accounts for a considerable part of the total decoding time for a speech recognizer. This is especially apparent in tasks that incorporate large vocabularies and long-dependency n-gram grammars, since these impose a high degree of context dependency and HMMs have to be treated differently in each context. This paper proposes a strategy for acoustic match of typical continuous density HMMs, decoupled from the main search and conducted as a separate component suited for parallelization. Instead of computing a large amount of probabilities for different alignments of each HMM, the proposed method computes all alignments, but more efficiently. Each HMM is matched only once against any time interval, and thus may be instantly looked up by the main search algorithm as required. In order to accomplish this in real time, a fast time-warping match algorithm is proposed, exploiting the specifics of the 3-state left-to-right HMM topology without skips. In proof-of-concept tests, using a highly optimized SIMD-parallel implementation, the algorithm was able to perform time-synchronous decoupled evaluation of a triphone acoustic model, with maximum phone duration of 40 frames, with a real-time factor of 0.83 on one of the CPUs of a Dual-Xeon 2 GHz workstation. The algorithm was able to compute the likelihood for 636,000 locally optimal HMM paths/second, with full state evaluation.

Place, publisher, year, edition, pages
2004. Vol. 42, no 2, 191-206 p.
Keyword [en]
HMM, acoustic match, parallel, large vocabulary speech recognition, search
National Category
Social Sciences Interdisciplinary
URN: urn:nbn:se:kth:diva-23223DOI: 10.1016/j.specom.2003.08.005ISI: 000189377800004ScopusID: 2-s2.0-1142300553OAI: diva2:341921
QC 20100525 QC 20111031Available from: 2010-08-10 Created: 2010-08-10 Last updated: 2011-10-31Bibliographically approved
In thesis
1. Efficient Methods for Automatic Speech Recognition
Open this publication in new window or tab >>Efficient Methods for Automatic Speech Recognition
2003 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [en]

This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on methods for increasing the efficiency of speech recognition systems and on techniques for efficient representation of different types of knowledge in the decoding process. In this work, several decoding algorithms and recognition systems have been developed, aimed at various recognition tasks.

The thesis presents the KTH large vocabulary speech recognition system. The system was developed for online (live) recognition with large vocabularies and complex language models. The system utilizes weighted transducer theory for efficient representation of different knowledge sources, with the purpose of optimizing the recognition process.

A search algorithm for efficient processing of hidden Markov models (HMMs) is presented. The algorithm is an alternative to the classical Viterbi algorithm for fast computation of shortest paths in HMMs. It is part of a larger decoding strategy aimed at reducing the overall computational complexity in ASR. In this approach, all HMM computations are completely decoupled from the rest of the decoding process. This enables the use of larger vocabularies and more complex language models without an increase of HMM-related computations.

Ace is another speech recognition system developed within this work. It is a platform aimed at facilitating the development of speech recognizers and new decoding methods.

A real-time system for low-latency online speech transcription is also presented. The system was developed within a project with the goal of improving the possibilities for hard-of-hearing people to use conventional telephony by providing speech-synchronized multimodal feedback. This work addresses several additional requirements implied by this special recognition task.

Place, publisher, year, edition, pages
Stockholm: KTH, 2003. iii, 65 p.
Trita-TMH, ISSN 1104-5787 ; 2003:14
speech recognition, algorithms, hidden markov models, HMM, weigted finite-state transducers
urn:nbn:se:kth:diva-3675 (URN)91-7283-657-1 (ISBN)
Public defence
2003-12-17, 00:00
QC 20100811Available from: 2003-12-11 Created: 2003-12-11 Last updated: 2010-08-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Seward, Alexander
By organisation
Speech, Music and Hearing
In the same journal
Speech Communication
Social Sciences Interdisciplinary

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 63 hits
ReferencesLink to record
Permanent link

Direct link