Feature enhancement by speaker-normalized splice for robust speech recognition.
Yusuke ShinoharaTakashi MasukoMasami AkaminePublished in: ICASSP (2008)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- automatic speech recognition
- speech processing
- speaker identification
- language model
- speech signal
- cepstral coefficients
- speech synthesis
- pattern recognition
- speech recognizer
- speech understanding
- speaker diarization
- image processing
- speaker verification
- speaker dependent
- speech recognition systems
- speaker independent
- speech recognition technology
- feature set
- feature vectors
- neural network
- isolated word
- speaker adaptation
- keyword spotting
- background noise
- computer vision
- information retrieval