Compensation of SNR and noise type mismatch using an environmental sniffing based speech recognition solution.
Yongjoo ChungJohn H. L. HansenPublished in: EURASIP J. Audio Speech Music. Process. (2013)
Keyphrases
- speech recognition
- noisy environments
- signal to noise ratio
- noise reduction
- hidden markov models
- noisy speech
- speech enhancement
- speech signal
- speech processing
- speech synthesis
- automatic speech recognition
- speech understanding
- language model
- pattern recognition
- speech recognizer
- speaker identification
- speech recognition technology
- neural network
- background noise
- speech recognition systems
- noise level
- keyword spotting
- speaker adaptation
- vocal tract
- speaker independent
- cepstral coefficients
- speech retrieval