On binary and ratio time-frequency masks for robust speech recognition.
Soundararajan SrinivasanNicoleta RomanDeLiang WangPublished in: INTERSPEECH (2004)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- speech signal
- speech processing
- automatic speech recognition
- speech synthesis
- language model
- speech recognition technology
- speech understanding
- speech recognizer
- speaker identification
- isolated word
- pattern recognition
- speaker dependent
- keyword spotting
- edge detection
- background noise
- speaker independent
- speech recognition systems
- signal processing
- speaker recognition
- handwriting recognition
- wavelet transform
- noise reduction
- cepstral coefficients
- speech recognition errors
- speech retrieval
- image processing
- speech recognizers
- machine learning