Progressive Joint Modeling in Unsupervised Single-Channel Overlapped Speech Recognition.
Zhehuai ChenJasha DroppoJinyu LiWayne XiongPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2018)
Keyphrases
- speech recognition
- single channel
- language model
- pattern recognition
- speech synthesis
- hidden markov models
- automatic speech recognition
- speech recognizer
- speech signal
- multi channel
- noisy environments
- speech enhancement
- speaker identification
- speech recognition systems
- machine learning
- computer vision
- frequency domain