A robust endpoint detection of speech for noisy environments with application to automatic speech recognition.
Sahar E. Bou-GhazaleKhaled AssalehPublished in: ICASSP (2002)
Keyphrases
- noisy environments
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- speech enhancement
- endpoint detection
- hidden markov models
- background noise
- speaker verification
- digit recognition
- speaker identification
- noise reduction
- broadcast news
- speech corpus
- word recognition
- conversational speech
- recognition errors
- voice activity detection
- spoken words
- spontaneous speech
- speech recognizer
- speech synthesis
- acoustic models
- speech recognizers
- speech sounds
- maximum likelihood
- pattern recognition