Joint Speech Recognition and Speaker Diarization via Sequence Transduction.
Laurent El ShafeyHagen SoltauIzhak ShafranPublished in: INTERSPEECH (2019)
Keyphrases
- speaker diarization
- speech recognition
- hidden markov models
- speaker identification
- automatic speech recognition
- speech recognizer
- pattern recognition
- speech signal
- noisy environments
- language model
- speech synthesis
- handwriting recognition
- broadcast news
- neural network
- image processing
- image classification
- probabilistic model
- image retrieval
- speaker verification
- computer vision