Towards robustness to fast speech in ASR.
Nikki MirghaforiEric Fosler-LussierNelson MorganPublished in: ICASSP (1996)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- spontaneous speech
- word error rate
- noisy environments
- speech corpus
- conversational speech
- spoken words
- speech retrieval
- speech synthesis
- broadcast news
- speaker identification
- language model
- database
- speech recognizers
- speech recognizer
- vocal tract
- hidden markov models
- website
- speech sounds
- high robustness
- multi stream
- error rate
- data sets