VADOI: Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition.
Jinhan WangXiaosu TongJinxi GuoDi HeRoland MaasPublished in: CoRR (2022)
Keyphrases
- end to end
- speech recognition
- voice activity detection
- noisy environments
- hidden markov models
- speech recognizer
- speech signal
- automatic speech recognition
- pattern recognition
- speech synthesis
- congestion control
- speech processing
- language model
- speech recognition systems
- speaker identification
- speaker independent
- speech recognition technology
- speech retrieval
- isolated word
- bayesian networks
- speaker dependent