Single-channel dereverberation by feature mapping using cascade neural networks for robust distant speaker identification and speech recognition.
Aditya Arie NugrahaKazumasa YamamotoSeiichi NakagawaPublished in: EURASIP J. Audio Speech Music. Process. (2014)
Keyphrases
- speaker identification
- speech recognition
- noisy environments
- speech enhancement
- single channel
- neural network
- speech signal
- pattern recognition
- multi channel
- speaker independent
- gaussian mixture model
- speaker dependent
- hidden markov models
- language model
- automatic speech recognition
- feature extraction
- feature vectors
- broadcast news
- sound source
- multiresolution
- machine learning