Loss recovery through spectral interpolation for robust speech recognition over packet voice communications.
Amr H. Nour-EldinHesham TolbaDouglas D. O'ShaughnessyPublished in: EUSIPCO (2004)
Keyphrases
- speech recognition
- noisy environments
- speech synthesis
- language model
- speech recognition errors
- hidden markov models
- speech signal
- speaker adaptation
- cepstral coefficients
- pattern recognition
- voice activity detection
- speech recognizer
- automatic speech recognition
- speech recognition technology
- speech recognition systems
- speech processing
- speaker identification
- speech understanding
- text to speech
- speaker independent
- speech recognizers
- isolated word
- neural network
- packet loss
- multispectral
- speaker dependent
- video data