Developments in Large Vocabulary Dictation : The LIMSI Nov 94 NAB System yJ

نویسنده

  • L. Lamel
چکیده

In this paper we report on our development work in large vocabulary , American English continuous speech dictation on the ARPA NAB task in preparation for the November 1994 evaluation. We have experimented with (1) alternative analyses for the acoustic front end, (2) the use of an enlarged vocabulary of 65k words so as to reduce the number of errors due to out-of-vocabulary words, (3) extensions to the lexical representation, (4) the use of additional acoustic training data, and (5) modiication of the acoustic models for telephone speech. The recognizer was evaluated on Hubs 1 and 2 of the fall 1994 ARPA NAB CSR Hub and Spoke Benchmark test. Experimental results on development and evaluation test data are given, as well as an analysis of the errors on the development data.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Developments in continuous speech dictation using the ARPA WSJ task

In this paper we report on our recent development work in large vocabulary,American English continuous speech dictation. We have experimented with (1) alternative analyses for the acoustic front end, (2) the use of an enlarged vocabulary so as to reduce the number of errors due to out-of-vocabulary words, (3) extensions to the lexical representation, (4) the use of additional acoustic training ...

متن کامل

Developments in continuous speech dictation using the 1995 ARPA NAB news task

In this paper we report on the LIMSI recognizer evaluated in the ARPA 1995 North American Business (NAB) News benchmark test. In contrast to previous evaluations, the new Hub 3 test aims at improving basic SI, CSR performance on unlimitedvocabulary read speech recorded under more varied acoustical conditions (background environmental noise and unknown microphones). The LIMSI recognizer is an HM...

متن کامل

Speaker-independent continuous speech dictation

In this paper we report progress made at LIMSI in speaker-independent large vocabulary speech dictation using newspaper speech corpora. The recognizer makes use of continuous density HMM with Gaussian mixture for acoustic modeling and n-gram statistics estimated on the newspaper texts for language modeling. Acoustic modeling uses cepstrum-based features, contextdependent phone models (intra and...

متن کامل

The LIMSI continuous speech dictation system: evaluation on the ARPA Wall Street Journal task

In this paper we report progress made at LIMSI in speakerindependent large vocabulary speech dictation using the ARPA Wall Street Journal-based CSR corpus. The recognizer makes use of continuous density HMM with Gaussian mixture for acoustic modeling and n-gram statistics estimated on the newspaper texts for language modeling. The recognizer uses a time-synchronous graph-search strategy which i...

متن کامل

The LIMSI 1995 Hub3 System

In this paper we report on the LIMSI recognizer evaluated in the ARPA 1995 North American Business (NAB) News Hub 3 benchmark test. The LIMSI recognizer is an HMM-based system with Gaussian mixture. Decoding is carried out in multiple forward acoustic passes, where more refined acoustic and language models are used in successive passes and information is transmitted via word graphs. In order to...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1995