4 papers
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Jiaxu Zhu, Weinan Tong, Yaoxun Xu +6
Mapping two modalities, speech and text, into a shared representation space, is a research topic of using text-only data to improve end-to-end automatic speech recognition (ASR) pe…
SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge
Jiaxu Zhu, Changhe Song, Zhiyong Wu +1
Recently, excellent progress has been made in speech recognition. However, pure data-driven approaches have struggled to solve the problem in domain-mismatch and long-tailed data.…
Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information
Jie Chen, Changhe Song, Deyi Tuo +4
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic in…
A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
Xueyuan Chen, Changhe Song, Yixuan Zhou +4
The accuracy of prosodic structure prediction is crucial to the naturalness of synthesized speech in Mandarin text-to-speech system, but now is limited by widely-used sequence-to-s…