Proceedings ArticleDOI
An approach to continuous speech recognition based on layered self-adjusting decoding graph
Qiru Zhou,Wu Chou +1 more
- Vol. 3, pp 1779-1782
Reads0
Chats0
TLDR
An approach to continuous speech recognition based on a layered self-adjusting decoding graph that utilizes a scaffolding layer to support fast network expansion and releasing and introduces self- adjusting capability in dynamic decoding on a general re-entrant decoding network.Abstract:
In this paper, an approach to continuous speech recognition based on a layered self-adjusting decoding graph is described. It utilizes a scaffolding layer to support fast network expansion and releasing. A two level hashing structure is also described. It introduces self-adjusting capability in dynamic decoding on a general re-entrant decoding network. In stack decoding, the scaffolding layer in the proposed approach enables the decoder to look several layers into the future so that long span inter-word context dependency can be exactly preserved. Experimental results indicate that highly efficient decoding can be achieved with a significant savings on recognition resources.read more
Citations
More filters
Journal ArticleDOI
Dynamic programming search for continuous speech recognition
Hermann Ney,S. Ortmanns +1 more
TL;DR: A unifying view of the dynamic programming approach to the search problem from the statistical point-of-view is given and how the search space results from the acoustic and language models required by the statistical approach are shown.
Journal ArticleDOI
Progress in dynamic programming search for LVCSR
Hermann Ney,S. Ortmanns +1 more
TL;DR: This work attempts to review the use of dynamic programming search strategies for large-vocabulary continuous speech recognition (LVCSR) by searching using a lexical tree, language-model look-ahead and word-graph generation.
Proceedings Article
A Reverse Turing Test using speech
TL;DR: This paper describes a Reverse Turing Test using speech and presents a test that depends on the fact that human recognition of distorted speech is far more robust than automatic speech recognition techniques.
Journal ArticleDOI
Robust decision tree state tying for continuous speech recognition
W. Reichl,Wu Chou +1 more
TL;DR: A new two-level segmental clustering approach is devised which combines the decision tree based state tying with agglomerative clustering of rare acoustic phonetic events.
Proceedings ArticleDOI
Progress in dynamic programming search for LVCSR
Hermann Ney,S. Ortmanns +1 more
TL;DR: This work attempts to review the use of dynamic programming search strategies for large-vocabulary continuous speech recognition (LVCSR) by searching using a lexical tree, language-model look-ahead and word-graph generation.
References
More filters
Book
Principles of Artificial Intelligence
TL;DR: This classic introduction to artificial intelligence describes fundamental AI ideas that underlie applications such as natural language processing, automatic programming, robotics, machine vision, automatic theorem proving, and intelligent data retrieval.
Proceedings ArticleDOI
A one pass decoder design for large vocabulary recognition
TL;DR: This paper shows that time-synchronous one-pass decoding using cross-word triphones and a trigram language model can be implemented using a dynamically built tree-structured network and is relatively efficient in implementation.
Journal ArticleDOI
A frame-synchronous network search algorithm for connected word recognition
Chin-Hui Lee,Lawrence R. Rabiner +1 more
TL;DR: A description is given of an implementation of a novel frame-synchronous network search algorithm for recognizing continuous speech as a connected sequence of words according to a specified grammar that is inherently based on hidden Markov model (HMM) representations.
Proceedings ArticleDOI
An efficient A* stack decoder algorithm for continuous speech recognition with a stochastic language model
TL;DR: A modified version of the algorithm which includes the full (forward) decoder, cross-word acoustic models and longer-span language models is described, which has been demonstrated to have a low probability of search error and to be very efficient.
Proceedings ArticleDOI
An efficient A* stack decoder algorithm for continuous speech recognition with a stochastic language model
TL;DR: A modified version of the Viterbi A* search algorithm is described which includes the full (forward) decoder, cross-word acoustic models and longer-span language models and is demonstrated to have a low probability of search error and to be very efficient.
Related Papers (5)
Decision tree state tying based on segmental clustering for acoustic modeling
W. Reichl,Wu Chou +1 more