A comparison of several acoustic representations for speech recognition with degraded and undegraded speech.
Melvyn J. HuntClaude LefèbvrePublished in: ICASSP (1989)
Keyphrases
- speech recognition
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- automatic speech recognition
- speech recognizer
- speech signal
- noisy speech
- speech synthesis
- hidden markov models
- language model
- speech processing
- speech recognition technology
- speaker identification
- pattern recognition
- speaker dependent
- word error rate
- acoustic features
- noisy environments
- keyword spotting
- recognition engine
- cepstral coefficients
- mel frequency cepstral coefficients
- speaker adaptation
- speech retrieval
- speaker recognition
- handwriting recognition
- speech enhancement
- computer vision
- isolated word