Harmonicity Based Dereverberation for Improving Automatic Speech Recognition Performance and Speech Intelligibility.
Keisuke KinoshitaTomohiro NakataniMasato MiyoshiPublished in: IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (2005)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- hidden markov models
- broadcast news
- conversational speech
- speech corpus
- spoken words
- speech recognizers
- spontaneous speech
- speech recognizer
- speech retrieval
- recognition errors
- phoneme recognition
- speech synthesis
- acoustic features
- speech sounds
- pattern recognition
- speaker identification
- handwriting recognition
- speech recognition systems
- word recognition
- noisy environments
- language model
- computer vision
- speech segments
- non stationary
- speaker dependent
- neural network
- formant frequencies