Cepstral noise subtraction for robust automatic speech recognition.
Robert RehrTimo GerkmannPublished in: ICASSP (2015)
Keyphrases
- automatic speech recognition
- noisy environments
- speech recognition
- speech signal
- speaker verification
- hidden markov models
- noise reduction
- pattern recognition
- word error rate
- language model
- conversational speech
- recognition errors
- spoken words
- machine learning
- speech recognizer
- cross correlation
- broadcast news
- linear prediction
- word recognition
- signal to noise ratio
- speech retrieval
- feature extraction