Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition.
Zhehuai ChenJasha DroppoPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- single channel
- multi channel
- speech signal
- hidden markov models
- automatic speech recognition
- language model
- speech recognizer
- speech synthesis
- pattern recognition
- speech recognition systems
- speech enhancement
- speaker identification
- noisy environments
- machine learning
- image quality
- signal processing
- training data
- multimedia
- computer vision
- data mining