2 papers
cs.CL2022
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Dong-Ho Lee, Akshen Kadakia, Brihi Joshi +8
NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging ai…
eess.AS2022
Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-end
Rem Hida, Masaki Hamada, Chie Kamada +3
Although end-to-end text-to-speech (TTS) models can generate natural speech, challenges still remain when it comes to estimating sentence-level phonetic and prosodic information fr…