Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation.
Xue YangChangchun BaoPublished in: INTERSPEECH (2022)
Keyphrases
- speaker independent
- speech recognition
- speaker dependent
- speaker identification
- hidden markov models
- speech recognizer
- convolutional network
- digit recognition
- speech recognition systems
- speech signal
- convolutional neural networks
- acoustic models
- automatic speech recognition
- language model
- speaker adaptation
- pattern recognition
- noisy environments
- speaker recognition
- broadcast news
- gaussian mixture model
- spoken language
- coarse to fine
- image classification
- image retrieval
- multiscale