Results 11 - 20 of 379

A Real-World Large Vocabulary Speaker-Independent Speech Recognition System

by Haixin Chai, Fang Zheng, Wenhu Wu, Ditang Fang
"... In this paper a real-world speaker-independent speech recognition system with 2000 Chinese phrases is introduced. Several new technologies, such as knowledge leading recognition strategy, the CDCPM acoustic model and a giant real-world speech database are used in this system, which help it gain very ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
In this paper a real-world speaker-independent speech recognition system with 2000 Chinese phrases is introduced. Several new technologies, such as knowledge leading recognition strategy, the CDCPM acoustic model and a giant real-world speech database are used in this system, which help it gain

Vocabulary and Environment Adaptation in Vocabulary-Independent Speech Recognition

by Hsiao-wuen Hon, Kai-fu Lee
"... In this paper, we are looking into the adaptation issues of vocabulary-independent (VI) systems. Just as with speaker-adaptation i speaker-independent system, two vocabulary adaptation algorithms [5] are implemented in order to tailor the VI subword models to the target vocabulary. The first algorit ..."
Abstract - Add to MetaCart
In this paper, we are looking into the adaptation issues of vocabulary-independent (VI) systems. Just as with speaker-adaptation i speaker-independent system, two vocabulary adaptation algorithms [5] are implemented in order to tailor the VI subword models to the target vocabulary. The first

Fast Speaker Independent Large Vocabulary Continuous Speech Recognition

by Doktors Der Ingenieurwissenschaften, Monika Woszczyna, Co-advisor Prof, Dr. W. Ward , 1998
"... To build useful applications based on large vocabulary continuous speech recognition systems, such systems have to run in real time on common platforms. However, with most research focused on further reducing the recognition error rates, the topic of speed has been neglected in the development of sp ..."
Abstract - Add to MetaCart
of speech recognition algorithms. I will present a speaker independent system that has been designed for fast speech recognition using vocabularies up to 65,000 words. Using the approaches presented in this thesis, this recognizer can now run in real time, 200 times faster than the original evaluation

Learning Sub-Word Units for Open Vocabulary Speech Recognition

by Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya Rastrow
"... Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems; new words can ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems; new words can

Speaker-Independent Continuous Speech Dictation

by J. L. Gauvain, L. F. Lamel, G. Adda, M. Adda-Decker - SPEECH COMMUNICATION , 1994
"... In this paper we report on progress made at LIMSI in speaker-independent large vocabulary speech dictation using newspaper-based speech corpora in English and French. The recognizer makes use of continuous density HMMs with Gaussian mixtures for acoustic modeling and n-gram statistics estimated on n ..."
Abstract - Cited by 32 (12 self) - Add to MetaCart
In this paper we report on progress made at LIMSI in speaker-independent large vocabulary speech dictation using newspaper-based speech corpora in English and French. The recognizer makes use of continuous density HMMs with Gaussian mixtures for acoustic modeling and n-gram statistics estimated

Combined Optimisation of Baseforms and Model Parameters in Speech Recognition Based on Acoustic Subword Units

by Trym Holter, Torbjørn Svendsen - in Proc. IEEE Workshop on Automatic Speech Recognition , 1997
"... A major challenge in speech recognition is creating a lexicon which is robust to inter- and intra-speaker variations. This is even more so in speech recognisers based on non-linguistic units, e.g., acoustic subword units (ASWUs), since no standard pronunciation dictionaries are available. Thus the b ..."
Abstract - Cited by 7 (0 self) - Add to MetaCart
A major challenge in speech recognition is creating a lexicon which is robust to inter- and intra-speaker variations. This is even more so in speech recognisers based on non-linguistic units, e.g., acoustic subword units (ASWUs), since no standard pronunciation dictionaries are available. Thus

Large Vocabulary Speech Recognition in English and French

by J. L. Gauvain, L. F. Lamel, G. Adda, M. Adda-Decker , 1993
"... In this paper we report efforts at LIMSI in speaker independent large vocabulary speech recognition in French and in English. The recognizer makes use of continuous density HMM (CDHMM) with Gaussian mixture for acoustic modeling and n-gram statistics estimated on text material for language modeling. ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
In this paper we report efforts at LIMSI in speaker independent large vocabulary speech recognition in French and in English. The recognizer makes use of continuous density HMM (CDHMM) with Gaussian mixture for acoustic modeling and n-gram statistics estimated on text material for language modeling

Creating Large Subword Units For Speech Recogntion

by T. Pfau, M. Beham, W. Reichl, G. Ruske
"... This paper deals with the choice of suitable subword units (SWU) for a HMM based speech recognition system. Using demisyllables (including phonemes) as base units, an inventory of domain-specific larger sized subword units, so-called macro-demisyllables (MDS), is created. A quality measure for the a ..."
Abstract - Cited by 8 (0 self) - Add to MetaCart
This paper deals with the choice of suitable subword units (SWU) for a HMM based speech recognition system. Using demisyllables (including phonemes) as base units, an inventory of domain-specific larger sized subword units, so-called macro-demisyllables (MDS), is created. A quality measure

Improving Environmental Robustness In Large Vocabulary Speech Recognition

by P.C. Woodland, M.J.F. Gales, D. Pye , 1996
"... This paper describes techniques to improve the robustness of the HTK large vocabulary speech recognition system to non-ideal acoustic environments. The primary methods are single-pass retraining using stereo training data; parallel model combination which combines HMMs trained on clean data with est ..."
Abstract - Cited by 30 (5 self) - Add to MetaCart
This paper describes techniques to improve the robustness of the HTK large vocabulary speech recognition system to non-ideal acoustic environments. The primary methods are single-pass retraining using stereo training data; parallel model combination which combines HMMs trained on clean data

Automatic determination of sub-word units for automatic speech recognition

by Fiona Couper Kenney , 2008
"... Current automatic speech recognition (ASR) research is focused on recognition of continuous, spontaneous speech. Spontaneous speech contains a lot of variability in the way words are pronounced, and canonical pronunciations of each word are not true to the variation that is seen in real data. Two ..."
Abstract - Add to MetaCart
of the components of an ASR system are acoustic models and pronunciation models. The variation within spontaneous speech must be accounted for by these components. Phones, or context-dependent phones are typically used as the base subword unit, and one acoustic model is trained for each sub-word unit. Pronunciation
Results 11 - 20 of 379