Weight-Space Viterbi Decoding Based Spectral Subtraction for Reverberant Speech Recognition.
Sung Min BanHyung Soon KimPublished in: IEEE Signal Process. Lett. (2015)
Keyphrases
- speech recognition
- speech signal
- spectral subtraction
- hidden markov models
- automatic speech recognition
- speaker identification
- speech recognizer
- speech synthesis
- additive noise
- background noise
- linear prediction
- noisy environments
- language model
- noisy speech
- acoustic features
- speech recognition systems
- pattern recognition
- vocal tract
- speaker recognition
- sound source
- frequency domain
- speech enhancement