Temporal contrast normalization and edge-preserved smoothing of temporal modulation structures of speech for robust speech recognition.
Xugang LuShigeki MatsudaMasashi UnokiSatoshi NakamuraPublished in: Speech Commun. (2010)
Keyphrases
- speech recognition
- speech signal
- noisy environments
- hidden markov models
- automatic speech recognition
- speech synthesis
- language model
- speech processing
- speech recognizer
- speaker identification
- pattern recognition
- information retrieval
- speech recognition systems
- handwriting recognition
- speaker recognition
- speech recognition technology
- n gram
- vocal tract
- recognition engine
- keyword spotting
- speaker independent
- speech recognition errors
- isolated word
- speech recognizers
- speaker dependent
- cepstral coefficients
- acoustic models
- machine learning
- bayesian networks
- speaker verification