The vast majority of work in continuous speech recognition uses phoneme-like units as the basic recognition component. The work presented here investigates the practicability of syllable-like units as the building blocks for recognition. A phonetically annotated telephony database is analysed at the syllable level, and a set of syllable-based HMMs are built. Refinements including the introducti...

The current generation of continuous speech recognition systems claims to offer high accuracy (greater than 95 percent) speech recognition at natural speech rates (150 words per minute) on low-cost (under $2000) platforms. This paper presents a state-of-the-technology summary, along with insights the authors have gained through testing one such product extensively and other products superficial...

We address the problem of robust lip tracking, visual speech feature extraction, and sensor integration for audio-visual speech recognition applications. An appearance based model of the articulators, which represents linguistically important features, is learned from example images and is used to locate, track, and recover visual speech information. We tackle the problem of joint temporal mode...

The papers in this session focus on techniques for and applications of large-vocabulary continuous speech recognition. The technique oriented papers discuss techniques for channel compensation, fast search, acoustic modeling, and adaptive language modeling. The applications oriented papers discuss methods for using recognizers for language identification, speaker identification, speakersex iden...

This paper presents some of the recent research on speaker-independent continuous speech recognition at LIMSI including efforts in phone and word recognition for both French and English. Evaluation of an HMMbased phone recognizer on a subset of the BREF corpus, gives a phone accuracy of 67.1% with 35 context-independent phone models and 74.2% with 428 context-dependent phone models. The word ac...

The first paper, BBN1, presented by R.Schwartz, refreshingly started by recounting a series of experiments the first of which had not or only minimally, improved system performance. Algorithmic methods discussed included Linear Discriminant Analysis, Supervised Vector Quantization, Shared Mixture VQ, Deleted Estimation of Context Weights, MMI Estimation Using "N-Best" Alternatives, and Cross-Wo...

One of the important actions in the processing of languages is part-of-speech tagging. Against of this importance, although numerous models have been presented in different languages but there is few works have been done in Persian language. In this paper, a part-of-speech tagging system on Persian corpus by using hidden Markov model is proposed. Achieving to this goal, the main aspects of Pers...