Development of Cslu Lvcsr: the 1997 Darpa Hub4 Evaluation System
نویسندگان
چکیده
This paper presents the CSLU Broadcast News transcription system used in the DARPA 1997 evaluation. The system was built using the softwares developed for the CSLU LVCSR project started in January 1997. This 25K-word vocabulary system used continuous HMMs for acoustic modeling and the standard backo trigram as the language model. The search used a single pass decoder with MLLR based adaptation technique. Although on the standard DARPA 20k WSJ task our system obtained 11.6% word error, the 39% error on this year's evaluation suggests there are still many aspects need to be learned for a new comer like us.
منابع مشابه
Ibm's Lvcsr System for Transcription of Broadcast News Used in the 1997 Hub4 English Evaluation
This paper describes IBM's large vocabulary continuous speech recognition (LVCSR) system used in the 1997 Hub4 English evaluation. It focusses on extensions and improvements to the system used in the 1996 evaluation. The recognizer uses an additional 35 hours of training data over the one used in the 1996 Hub4 evaluation [8]. It includes a number of new features: optimal feature space for acous...
متن کاملTranscription of broadcast news-some recent improvements to IBM's LVCSR system
This paper describes extensions and improvements to IBM’s large vocabulary continuous speech recognition (LVCSR) system for transcription of broadcast news. The recognizer uses an additional 35 hours of training data over the one used in the 1996 Hub4 evaluation [?]. It includes a number of new features: optimal feature space for acoustic modeling (in training and/or testing), filler-word model...
متن کاملAcoustic Modeling for the SRI Hub4 Partitioned Evaluation Continuous Speech Recognition System
We describe the developmentof the SRI system evaluated in the 1996 DARPA continuous speech recognition (CSR) Hub4 partitioned evaluation (PE). The task for the Hub4 evaluation was to recognize speech from broadcast television and radio shows. Recognizingsuch speech by machines poses many challenges. First, the segments to be recognized could be very long. This introduces a problem in training a...
متن کاملDesign of Fast Lvcsr Systems
This paper describes the development of fast (less than 10 times real-time) large vocabulary continuous speech recognition (LVCSR) systems based on technology developed for unlimited runtime systems assembled for participation in recent DARPA/NIST LVCSR evaluations. A general system structure for 10 times real-time systems is proposed and two specific systems that have been built for Broadcast ...
متن کاملDevelopment of The RU Hub4 system
This paper describes preliminary development of a broadcast news transcribing system for this year's Hub4 evaluation. The recognition system uses CROWNS (developed at RU for the 1995 Hub3 tasks) with several modi cations to handle the news programming task. Features such as model adaptation have been added to quickly provide acoustic models thought appropriate for the new task, even though the ...
متن کامل