Sentence-hypotheses generation in a continuous-speech recognition system
نویسنده
چکیده
In this paper, the dynamic-programming algorithm for continuous-speech recognition is modified in orderto obtain a top-N sentence-hypotheses Iist instead of the usual one sentence only. The theoretical basis of this extension is a generalization of Bellman's principle of optimality. Due to the computational complexity of the new algorithm, a sub-optimal variant is proposed, and experimental results within the SPICOS system are presented.
منابع مشابه
A Prosodic/Syntactic Model for Integrating Prosody in a Continuous Speech Recognition System
This paper presents a statistical model, which associates syntactic rules with prosodic cues in order to help a continuous speech recognition system produce sentence hypotheses. The system consists of the sequential coupling of a standard speech recognizer and a syntactic parser working on lattices of hypotheses by means of a Stochastic Context -Free Grammar (SCFG). The prosodic/syntactic model...
متن کاملImproved Bayesian Training for Context-Dependent Modeling in Continuous Persian Speech Recognition
Context-dependent modeling is a widely used technique for better phone modeling in continuous speech recognition. While different types of context-dependent models have been used, triphones have been known as the most effective ones. In this paper, a Maximum a Posteriori (MAP) estimation approach has been used to estimate the parameters of the untied triphone model set used in data-driven clust...
متن کاملContinuous speech recognition with parse filtering
We propose “parse-filtering”, a new approach to continuous speech recognition. With it, word sequence hypotheses generated on the basis of N-gram language models are verified by grammar-based parsing during the search for the best-scoring hypothesis, and unparsable hypotheses are filtered out immediately as the search proceeds. Experimental results show that this method yields a higher sentence...
متن کاملSpoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting
Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIBchr('39')s archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کامل