Improving the role of unvoiced speech segments by spectral normalisation in robust speech recognition.
Carlos S. LimaLuís B. AlmeidaJoão L. MonteiroPublished in: INTERSPEECH (2002)
Keyphrases
- speech recognition
- speech signal
- automatic speech recognition
- speech retrieval
- speech segments
- noisy environments
- spectral analysis
- hidden markov models
- pattern recognition
- speaker diarization
- speech recognizer
- speaker adaptation
- language model
- speaker identification
- maximum likelihood
- neural network
- acoustic features
- speaker independent
- broadcast news
- probabilistic model
- speech recognition systems
- n gram
- similarity measure
- information retrieval