Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning.
Alexander H. LiuTao TuHung-yi LeeLin-Shan LeePublished in: CoRR (2019)
Keyphrases
- speech recognition
- speech signal
- speech processing
- hidden markov models
- automatic speech recognition
- speech synthesis
- language model
- speech recognizer
- speech recognition systems
- noisy environments
- pattern recognition
- speaker identification
- keyword spotting
- speaker recognition
- unsupervised learning
- speaker independent
- speech recognition technology
- image processing
- semi supervised
- neural network
- recognition engine
- word error rate
- non stationary
- speech recognizers
- audio visual speech recognition