Direct control on modulation spectrum for noise-robust speech recognition and spectral subtraction.
Naoya WadaNoboru HayasakaShingo YoshizawaYoshikazu MiyanagaPublished in: ISCAS (2006)
Keyphrases
- spectral subtraction
- speech recognition
- speech signal
- noisy environments
- language model
- hidden markov models
- automatic speech recognition
- pattern recognition
- noisy speech
- speech synthesis
- noise model
- speech enhancement
- speaker identification
- signal to noise ratio
- speech recognizer
- speech recognition systems
- training data
- speaker diarization
- denoising