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