Online detecting end times of spoken utterances for synchronization of live speech and its transcripts.
Jie GaoQingwei ZhaoYonghong YanPublished in: INTERSPEECH (2009)
Keyphrases
- automatic speech recognition
- spoken documents
- broadcast news
- speech sounds
- speech recognition
- speech segments
- speech transcripts
- speech signal
- spoken document retrieval
- spoken language
- spontaneous speech
- online learning
- real time
- speech retrieval
- speech recognizers
- hidden markov models
- content analysis
- automatically generated
- conversational speech
- spoken words
- question answering
- video search
- audio visual
- noisy environments
- multi stream
- human communication
- natural language processing
- natural language
- neural network