A linear projection approach to environment modeling for robust speech recognition.
Yu TsaoChien-Lin HuangShigeki MatsudaChiori HoriHideki KashiokaPublished in: ICASSP (2012)
Keyphrases
- speech recognition
- noisy environments
- linear projection
- hidden markov models
- speech synthesis
- language model
- speech processing
- speech signal
- pattern recognition
- speech recognition technology
- automatic speech recognition
- speech recognizer
- speaker identification
- speech recognition systems
- signal processing
- speaker dependent
- noise reduction
- image processing
- audio visual speech recognition
- optimization criterion
- word recognition
- cost function
- feature extraction