Towards Unsupervised Speech Recognition Without Pronunciation Models.
Junrui NiLiming WangYang ZhangKaizhi QianHeting GaoMark Hasegawa-JohnsonChang D. YooPublished in: CoRR (2024)
Keyphrases
- speech recognition
- acoustic models
- hidden markov models
- automatic speech recognition
- language model
- pattern recognition
- speech processing
- speech recognizer
- speech signal
- speech synthesis
- speech recognition technology
- speech understanding
- speaker independent
- unsupervised learning
- speaker identification
- probabilistic model
- computer vision
- em algorithm
- character recognition
- semi supervised
- speaker diarization
- speaker dependent