Template-Based Automatic Speech Recognition Meets Prosody.
Dino SeppiKris DemuynckDirk Van CompernollePublished in: INTERSPEECH (2011)
Keyphrases
- automatic speech recognition
- speech recognition
- speech synthesis
- hidden markov models
- speech signal
- word error rate
- conversational speech
- text to speech
- broadcast news
- spoken words
- noisy environments
- recognition errors
- language model
- acoustic features
- pattern recognition
- speech corpus
- speech retrieval
- spontaneous speech
- word recognition
- audio visual
- speaker adaptation
- multi modal
- vocal tract
- information retrieval
- speech sounds
- neural network