Using Convolution and Sequence-discriminative Training to Improving Children Speech Recognition.
Fanchang MengShouye PengGuohui ZhangPublished in: APSIPA (2019)
Keyphrases
- speech recognition
- discriminative training
- automatic speech recognition
- hidden markov models
- speech recognition technology
- speech signal
- speech recognizer
- language model
- pattern recognition
- acoustic models
- maximum likelihood
- speech synthesis
- noisy environments
- broadcast news
- probabilistic interpretation
- speaker independent
- word recognition
- speech recognition systems
- image processing
- speaker identification
- similarity measure
- information retrieval
- probability distribution