CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis.
Ji-Hoon KimHongsun YangYooncheol JuIlhwan KimByeongyeol KimPublished in: CoRR (2023)
Keyphrases
- speech recognition
- speaker independent
- speech synthesis
- cross lingual
- language modeling
- language model
- speech recognition systems
- hidden markov models
- machine translation
- pattern recognition
- vocal tract
- speech recognizer
- automatic speech recognition
- speech signal
- language independent
- speaker identification
- cross language
- statistical machine translation
- information retrieval
- noisy environments
- document retrieval
- word segmentation
- data mining
- face recognition
- test collection
- query expansion
- probabilistic model