E09-1024 experimentation with automatic speech transcriptions is interesting to test the robustness
D09-1112 experimentation with automatic speech transcriptions revealed that to test the robustness
D14-1098 Chinese Gale Phase 1 conversational speech transcriptions are used to generate a bilingual
D14-1098 Phase 1 English conversational speech transcription are used to train the English
D14-1098 Phase 1 Chinese conversational speech transcriptions are used to train a Chinese matrix
H94-1057 work as the general continuous speech transcription system or the general database
acl-2001-inv1 an important factor in making a speech transcription system viable for automatic indexation
H92-1068 all the available spontaneous speech transcriptions ( roughly 10,000 sentences )
H89-2078 Statistical language models in speech transcription have given the lowest perplexity
E12-2009 Ismael Abstract Current automatic speech transcription systems can achieve a high accuracy
H94-1014 and to applications other than speech transcription . 2 . MIXTURE LANGUAGE MODEL
H89-2078 of speech , etc. , but also in speech transcription . The error rate of speech recognition
acl-2001-inv1 and to produce enriched symbolic speech transcriptions . The ECHO project ( http://pc-erato2.iei.pi.cnr.it/echo
D12-1070 transcriptions . This creates an integrated speech transcription and translation framework . This
acl-2001-inv1 an important factor in making a speech transcription system viable for audio data
H01-1059 step in developing a " generic " speech transcription engine is to assess the most
D10-1046 network ( WCN ) , and the manual speech transcription ( Transcription ) . Speech transcription
E09-1002 e.g. named entity extraction or speech transcription ) for collections kept in technically
D14-1098 trained on the code switching speech transcription is 236 on the lecture speech
D11-1064 lattices is based on the 2007 IBM Speech transcription system for the GALE Distillation
hide detail