Improving children speech recognition in acoustically mismatched condition using eigenvoices and feature projections.
Hemant Kumar KathaniaSyed ShahnawazuddinRohit SinhaPublished in: NCC (2017)
Keyphrases
- speech recognition
- speech recognition technology
- hidden markov models
- cepstral coefficients
- language model
- speech synthesis
- automatic speech recognition
- speech processing
- speech signal
- speech recognizer
- noisy environments
- pattern recognition
- speaker identification
- speech recognition systems
- pilot study
- speech recognizers
- speech retrieval
- speech recognition errors
- speaker recognition
- students with learning disabilities
- feature set
- machine learning
- audio visual speech recognition