speech recognition system-13

speech recognition system-13





Phonetic modeling in the Philips Chinese continuous-speech recognition system
FREE DOWNLOAD
ABSTRACT We have extended the Philips large-vocabulary continuousspeech recognition system towards Chinese. On the way from our existing Western-language technology to Mandarin, the first step was to build a suitable phonetic model. This paper describes the

A hybrid learning vector quantization/time-delay neural networks system for the recognition of arabic speech
FREE DOWNLOAD
ABSTRACT In this paper, we present an approach which significantly improves the performances of automatic speech recognition systems (ASRSs) dedicated to Arabic language. We propose to combine a version of Learning Vector Quantization (LVQ) and

A scalable system for embeded large vocabulary continuous speech recognition
FREE DOWNLOAD
ABSTRACT This paper presents a system for large vocabulary continuous speech recognition in condition of constrained hardware resources. We investigate efficient pruning and caching strategy aiming to handle extensive acoustic and linguistic modeling.

Universal combined system: speech recognition, emotion recognition and talking head for deaf and hard of hearing people
FREE DOWNLOAD
ABSTRACT. The work presented here is an extension of the old LABIAO (Lecture lABIale Assiste par Ordinateur or Computer-Assisted lip reading) project. Its object is to provide lip readers and, especially deaf and hard of hearing people with an artificial talking head

AlfaNum System for Continuous Speech Recognition
FREE DOWNLOAD
ABSTRACT This paper shortly presents program package for continuous speech recognition which is, so far, successful with small and medium dictionaries. Package is very large because it contains both modules for training and recognition. Each of these modules

A Real-World Large Vocabulary Speaker-Independent Speech Recognition System
FREE DOWNLOAD
H Chai, F Zheng, W Wu ,somewhere in this proceeding ,cslt.riit.tsinghua.edu.cn ABSTRACT 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

A system for improving the recognition of fluently spoken German speech
FREE DOWNLOAD
It should be investigated, how far aspects of semantics and inferences could improve the automa- tic speech recognition. The work is part of a speech recognition system that receives speech sig- nals, converts them into forms suitable for further actions and finally puts out

An Isolated/Continuous Speech Recognition System on a Personal Computer
FREE DOWNLOAD
There are some speech recognition systems working on a personal computer without special hardwares. We also developed such a system, which was transfered from our spontaneous speech recognition system working on a Workstationm. On putting to

Speech recognition system of Arabic alphabet based on a telephony Arabic corpus
FREE DOWNLOAD
Automatic recognition of spoken alphabets is one of the difficult tasks in the field of computer speech recognition. In this research, spoken Arabic alphabets are investigated from the speech recognition problem point of view. The system is designed to recognize spelling of

Data Refining HMM, A New Approach to HMM Based Speech Recognition SystemImprovement
FREE DOWNLOAD
ABSTRACT The accuracy of HMM based speech recognition systems is limited due to some HMM presumptions. In this paper, a decorrelation method named data refining has been applied to HMM input sequence. The main idea in this study is to produce a nearly

A Speech Recognition System for Urdu Language
FREE DOWNLOAD
ABSTRACT This paper presents a speech processing and recognition system for individually spoken Urdu language words. The speech feature extraction was based on a dataset of 150 different samples collected from 15 different speakers. The data was pre-processed using

Model Distance and it s application on mixed language speech recognition system
FREE DOWNLOAD
G Fu ,To be appearred in ISCSLP 2000 ,colips.org ABSTRACT The failure of current mono language based Speech Recognition Systems in recognizing mixed language makes a need arise to establish a mixed system. One of the important items is how to define a good phone set in such a mixed system. This paper

NL-processor and linguistic Knowledge Base in a speech recognition system The linguistic methods providing grammatical and lexical control of the acoustic recognition results are described. The Parser (NL-Processor) uses original local grammar, ATN-type grammar, and comprehensive computer dictionaries (Linguistic Knowledge Base-LKB).

A Connectionist Framework For Feature Based Speech Recognition System Using Artificial Neural Networks
FREE DOWNLOAD
In this paper we study the various methods employed to recognize discrete speech.We de- sign a recognition system which is capable of recognizing spoken language. The soft- ware takes spoken language and translates it into written text, or follow the spoken in- structions to

A High-Performance Hardware Speech Recognition System for Mobile Applications
FREE DOWNLOAD
ABSTRACT While commercial speech recognition systems remain limited in their capabilities, research systems are now relatively mature, although computationally expensive. Specialized hardware is one solution to this problem, and certainly the only solution at

Using audio quality to predict word error rate in an automatic speech recognition system
FREE DOWNLOAD
ABSTRACT Faced with a backlog of audio recordings, users of automatic speech recognition (ASR) systems would benefit from the ability to predict which files would result in useful output transcripts in order to prioritize processing resources. ASR systems used in

Development of a speech recognition system using a sparse training corpus
FREE DOWNLOAD
ABSTRACT Text corpus size is an important issue when building a language model (LM). This is a particularly important issue for languages where little data is available. This paper introduces a LM adaptation technique to improve a LM built using a small amount of task

Speech Corpus Development for a Speaker Independent Spontaneous Urdu Speech Recognition System
FREE DOWNLOAD
ABSTRACT This paper reports the design and development of an 82 speaker Urdu speech corpus for speaker independent spontaneous speech recognition using the CMU Sphinx Open Source Toolkit for Speech Recognition. The corpus consists of 45 hours of

Comparative analysis of arabic vowels using formants and an automatic speech recognition system
FREE DOWNLOAD
ABSTRACT Arabic, the world s second most spoken language in terms of number of speakers, has not received much attention from the traditional speech processing research community. This study is specifically concerned with the analysis of vowels in modern standard Arabic

Related

speech recognition system-12

speech recognition system-14 CSE PROJECTS

FREE IEEE PAPER AND PROJECTS

FREE IEEE PAPER