Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers.
Naoyuki KandaYashesh GaurXiaofei WangZhong MengZhuo ChenTianyan ZhouTakuya YoshiokaPublished in: CoRR (2020)
Keyphrases
- speech recognition
- speaker identification
- speaker dependent
- speech signal
- speech processing
- speaker recognition
- hidden markov models
- automatic speech recognition
- speech synthesis
- speaker independent
- speech recognizer
- noisy environments
- language identification
- probabilistic neural network
- language model
- pattern recognition
- speech recognition technology
- speech recognition systems
- broadcast news
- gaussian mixture model
- machine learning
- vocal tract
- feature extraction
- neural network
- mel frequency cepstral coefficients
- acoustic models
- speaker adaptation
- noisy speech