Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization.
Zhihong LeiErnest PusateriShiyi HanLeo LiuMingbin XuTim NgRuchir TravadiYouyuan ZhangMirko HannemannMan-Hung SiuZhen HuangPublished in: CoRR (2023)
Keyphrases
- end to end
- speech recognition
- automatic speech recognition
- broadcast news
- speech recognizer
- spontaneous speech
- spoken document retrieval
- speech signal
- language model
- hidden markov models
- speaker independent
- acoustic models
- admission control
- multipath
- speaker identification
- grapheme to phoneme conversion
- ad hoc networks
- n gram
- scalable video
- congestion control
- wireless ad hoc networks
- named entities
- transport layer
- high bandwidth
- content delivery
- context aware
- spoken language
- application layer
- real time