Low-memory fast on-line adaptation for acoustically mismatched children's speech recognition.
Syed ShahnawazuddinRohit SinhaPublished in: INTERSPEECH (2015)
Keyphrases
- speech recognition
- low memory
- speech recognition technology
- speaker adaptation
- speech signal
- language model
- speech synthesis
- hidden markov models
- speech processing
- speech recognizer
- automatic speech recognition
- pattern recognition
- memory requirements
- speaker identification
- students with learning disabilities
- noisy environments
- transform coding
- speech recognition systems
- speech recognizers
- speaker independent
- signal processing
- multimedia
- information retrieval
- neural network