CROSSSPEECH: Speaker-Independent Acoustic Representation for Cross-Lingual Speech Synthesis.
Ji-Hoon KimHongsun YangYooncheol JuIlhwan KimByeongyeol KimPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- speaker independent
- speech synthesis
- cross lingual
- language modeling
- language model
- hidden markov models
- speech recognition systems
- vocal tract
- machine translation
- speech signal
- speech recognizer
- language independent
- pattern recognition
- speaker identification
- automatic speech recognition
- parallel corpus
- cross language
- n gram
- noisy environments
- query translation
- data mining
- knowledge representation
- bayesian networks
- information retrieval
- machine learning