Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition.
Chen XuXiaoqian LiuErfeng HeYuhao ZhangQianqian DongTong XiaoJingbo ZhuDapeng ManWu YangPublished in: CoRR (2023)
Keyphrases
- speech recognition
- target language
- source language
- language resources
- parallel corpus
- machine translation
- machine translation system
- bilingual dictionaries
- comparable corpora
- isolated word
- automatic speech recognition
- cross language information retrieval
- query translation
- speech synthesis
- broadcast news
- parallel corpora
- speech signal
- hidden markov models
- language model
- speech recognizer
- statistical machine translation
- speech processing
- speech recognition technology
- cross lingual
- speaker identification
- multilingual retrieval
- noisy environments
- speech recognition systems
- pattern recognition
- cross language
- recognition engine
- translation model
- word error rate
- multi modal
- natural language
- language processing
- language modeling
- keyword spotting
- natural language processing
- language independent
- speaker independent
- speaker dependent
- speech recognizers
- neural network
- n gram
- speaker adaptation
- cepstral coefficients
- speech retrieval
- image processing