Differences between acoustic characteristics of spontaneous and read speech and their effects on speech recognition performance.
Masanobu NakamuraKoji IwanoSadaoki FuruiPublished in: Comput. Speech Lang. (2008)
Keyphrases
- speech recognition
- speech recognition systems
- speaker independent
- speech recognizers
- speech recognizer
- acoustic models
- speech signal
- automatic speech recognition
- speech synthesis
- noisy speech
- language model
- hidden markov models
- speech processing
- pattern recognition
- speaker dependent
- speech recognition technology
- isolated word
- acoustic features
- statistically significant
- speaker identification
- conversational speech
- noisy environments
- word error rate
- recognition engine
- speech recognition errors
- broadcast news
- neural network