Articulatory feature based continuous speech recognition using probabilistic lexical modeling. (March 2016)

• Record Type: Journal Article
• Authors: Rasipuram, Ramya; Magimai.-Doss, Mathew
• Is Part Of: Computer speech & language. Volume 36(2016)
• Page Start: 233
• Page End: 259
• Publication Date: 2016-03
• Subjects: Automatic speech recognition -- Articulatory features -- Probabilistic lexical modeling -- Kullback–Leibler divergence based hidden Markov model -- Phoneme subword units -- Grapheme subword units; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2015.04.003
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract : Highlights: Approach for AF-based ASR in framework of probabilistic lexical modeling is proposed. Most approaches in literature use a knowledge-based deterministic phoneme-to-AF map. Approach incorporates a probabilistic phoneme-to-AF map learned through acoustic data. Analysis has shown that the approach allows different AFs to evolve asynchronously. Approach has potential to reduce word error rates by incorporating AFs in an ASR system. Abstract: Phonological studies suggest that the typical subword units such as phones or phonemes used in automatic speech recognition systems can be decomposed into a set of features based on the articulators used to produce the sound. Most of the current approaches to integrate articulatory feature (AF) representations into an automatic speech recognition (ASR) system are based on a deterministic knowledge-based phoneme-to-AF relationship. In this paper, we propose a novel two stage approach in the framework of probabilistic lexical modeling to integrate AF representations into an ASR system. In the first stage, the relationship between acoustic feature observations and various AFs is modeled. In the second stage, a probabilistic relationship between subword units and AFs is learned using transcribed speech data. Our studies on a continuous speech recognition task show that the proposed approach effectively integrates AFs into an ASR system. Furthermore, the studies show that either phonemes or graphemes can be used as subword units. Analysis of the probabilistic relationship captured by the parameters has shown that the approach is capable of adapting the knowledge-based phoneme-to-AF representations using speech data; and allows different AFs to evolve asynchronously.