Zobrazeno 1 - 10 of 17 pro vyhledávání: '"Lifa Sun"'
3
Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initialization
Autor: Jianwei Yu, Lifa Sun, Xunying Liu, Helen Meng, Disong Wang, Xixin Wu
Publikováno v: ISCSLP
Dysarthric speech recognition is a challenging task as dysarthric data is limited and its acoustics deviate significantly from normal speech. Model-based speaker adaptation is a promising method by using the limited dysarthric speech to fine-tune a b
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f68a5094202f20d98269e38b54986b4b
http://arxiv.org/abs/2011.01686
Zobrazit plný text záznamu
4
End-To-End Accent Conversion Without Using Native Utterances
Autor: Xunying Liu, Helen Meng, Dan Su, Xixin Wu, Yuewen Cao, Songxiang Liu, Shiyin Kang, Disong Wang, Lifa Sun, Zhiyong Wu, Dong Yu
Publikováno v: ICASSP
Techniques for accent conversion (AC) aim to convert non-native to native accented speech. Conventional AC methods try to convert only the speaker identity of a native speaker’s voice to that of the non-native accented target speaker, leaving the u
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cd6225b181f56543cbcf4e3b735d273a
https://doi.org/10.1109/icassp40776.2020.9053797
Zobrazit plný text záznamu
5
End-To-End Voice Conversion Via Cross-Modal Knowledge Distillation for Dysarthric Speech Reconstruction
Autor: Jianwei Yu, Disong Wang, Songxiang Liu, Xunying Liu, Helen Meng, Xixin Wu, Lifa Sun
Publikováno v: ICASSP
Dysarthric speech reconstruction (DSR) is a challenging task due to difficulties in repairing unstable prosody and correcting imprecise articulation. Inspired by the success of sequence-to-sequence (seq2seq) based text-to-speech (TTS) synthesis and k
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::63a0348fde8aeecb5e5c0e65dbdbf7c2
https://doi.org/10.1109/icassp40776.2020.9054596
Zobrazit plný text záznamu
6
Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion
Autor: Lifa Sun, Xixin Wu, Xunying Liu, Disong Wang, Helen Meng, Songxiang Liu
Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody while maintain
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8b8a7fa1226306a71362fcfe02c0e13
Zobrazit plný text záznamu
10
Feature Based Adaptation for Speaking Style Synthesis
Autor: Shiyin Kang, Xunying Liu, Zhiyong Wu, Xixin Wu, Songxiang Liu, Helen Meng, Lifa Sun
Publikováno v: ICASSP
Speaking style plays an important role in the expressivity of speech for communication. Hence speaking style is very important for synthetic speech as well. Speaking style adaptation faces the difficulty that the data of specific styles may be limite
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0216f830f6b1073397ff958ae6cc36db
https://doi.org/10.1109/icassp.2018.8462178
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje