Higher order cepstral moment normalization (HOCMN) for robust speech recognition.
Chang-Wen HsuLin-Shan LeePublished in: ICASSP (1) (2004)
Keyphrases
- speech recognition
- higher order
- noisy environments
- hidden markov models
- speech signal
- language model
- automatic speech recognition
- speech processing
- pattern recognition
- speech recognizer
- speech recognition systems
- speech synthesis
- speech recognition technology
- pairwise
- speaker independent
- speaker identification
- information retrieval
- isolated word
- speech understanding
- acoustic models
- visual features
- feature extraction