Unsupervised adaptation with domain separation networks for robust speech recognition.
Zhong MengZhuo ChenVadim MazalovJinyu LiYifan GongPublished in: ASRU (2017)
Keyphrases
- speech recognition
- noisy environments
- speaker adaptation
- hidden markov models
- language model
- speech recognizer
- speech recognition technology
- speech synthesis
- speech understanding
- speech processing
- automatic speech recognition
- speech signal
- speech recognition systems
- handwriting recognition
- semi supervised
- speaker identification
- pattern recognition
- speaker dependent
- speech recognizers
- unsupervised learning
- computer vision
- information retrieval
- speaker diarization
- speaker independent
- students with learning disabilities
- neural network