Rapid Speaker Adaptation of Neural Network Based Filterbank Layer for Automatic Speech Recognition.
Hiroshi SekiKazumasa YamamotoTomoyosi AkibaSeiichi NakagawaPublished in: SLT (2018)
Keyphrases
- speaker adaptation
- automatic speech recognition
- filter bank
- speech recognition
- subband
- image coding
- speech signal
- hidden markov models
- spectral analysis
- neural network
- multiresolution
- signal processing
- multiscale
- maximum likelihood
- computationally efficient
- wavelet transform
- speaker dependent
- frequency domain
- acoustic features
- pattern recognition
- speech recognizer
- noisy environments
- broadcast news
- speaker independent
- image compression
- language model
- speech synthesis