Journal ArticleDOI
Phoneme-Based Continuous-Speech Recognition in the SPICOS-II System
TLDR
An overview of a research system for phoneme-based large-vocabulary continuous-speech recognition that provides the speaker-dependent recognition component in the speech-understanding system SPICOS that is designed to recognize and understand database queries spoken in natural German language.Abstract:
This paper gives an overview of a research system for phoneme-based large-vocabulary continuous-speech recognition. The system provides the speaker-dependent recognition component in the speech-understanding system SPICOS that is designed to recognize and understand database queries spoken in natural German language. The recognition technique used in the SPICOS recognition system is based on an integrated approach that combines the various knowledge sources, such as an inventory of subword units, pronunciation lexicon and language model, during the process of decision making in order to improve the reliability of the acoustic recognition. The recognition problem then amounts to an efficient search for the globally optimal decision through a huge state space. The size of this state space depends primarily on the type of language model being used. Stochastic bigram and trigram models are studied and compared with the case of no language model restrictions. Recognition experiments have been carried out on a 917-word task for 4 speakers. For each speaker, 200 sentences totalling 1391 words had to be recognized.read more
Citations
More filters
Patent
Method and apparatus for recognizing the uttered words in a speech signal
Hermann Ney,Volker Steinbiss +1 more
TL;DR: In this paper, a language model value corresponding to this probability is added at boundaries between words to increase the reliability of coherent speech recognition, which models, for example, take into account the probabilities of word combinations, especially of word pairs.
Book ChapterDOI
Ein sprachverstehendes Dialogsystem zur Dattenbankabfrage - die Realisierung des SPICOS II-Prototypen
TL;DR: Das Workstation-basierende System, das optional sprecheradaptiv betrieben werden kann, enthalt dedizierte Hardware zur akustischen Vorverarbeitung und ein sprachverstehendes Dialogsystem realisiert.
References
More filters
Journal ArticleDOI
Estimation of probabilities from sparse data for the language model component of a speech recognizer
TL;DR: The model offers, via a nonlinear recursive procedure, a computation and space efficient solution to the problem of estimating probabilities from sparse data, and compares favorably to other proposed methods.
Journal ArticleDOI
Continuous speech recognition by statistical methods
TL;DR: Experimental results are presented that indicate the power of the methods and concern modeling of a speaker and of an acoustic processor, extraction of the models' statistical parameters and hypothesis search procedures and likelihood computations of linguistic decoding.
Journal ArticleDOI
The use of a one-stage dynamic programming algorithm for connected word recognition
TL;DR: The algorithm to be developed is essentially identical to one presented by Vintsyuk and later by Bridle and Brown, but the notation and the presentation have been clarified and the computational expenditure per word is independent of the number of words in the input string.
Proceedings ArticleDOI
Large vocabulary natural language continuous speech recognition
Lalit R. Bahl,Raimo Bakis,Jerome R. Bellegarda,Peter Fitzhugh Brown,David Burshtein,Subhro Das,P.V. de Souza,Ponani S. Gopalakrishnan,Frederick Jelinek,Dimitri Kanevsky,Robert Leroy Mercer,A. Nadas,David Nahamoo,Michael Picheny +13 more
TL;DR: A description is presented of the authors' current research on automatic speech recognition of continuously read sentences from a naturally-occurring corpus: office correspondence, which combines features from their current isolated-word recognition system and from their previously developed continuous-speech recognition system.
Book ChapterDOI
The development of an experimental discrete dictation recognizer
TL;DR: The paper outlines the self-organized, statistical approach underlying the basic algorithms of the recognizer, and considers important issues in the future development of dictation recognizers, such as vocabulary selection, language model creation, and human factors.