no code implementations • 5 Nov 2021 • Bi-Cheng Yan, Hsin-Wei Wang, Shih-Hsuan Chiu, Hsuan-Sheng Chiu, Berlin Chen
Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 13 Jun 2021 • Shih-Hsuan Chiu, Tien-Hong Lo, Fu-An Chao, Berlin Chen
In view of this, we in this paper seek to represent the historical context information of an utterance as graph-structured data so as to distill cross-utterances, global word interaction relationships.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 11 Apr 2021 • Shih-Hsuan Chiu, Berlin Chen
More recently, Bidirectional Encoder Representations from Transformers (BERT) was proposed and has achieved impressive success on many natural language processing (NLP) tasks such as question answering and language understanding, due mainly to its effective pre-training then fine-tuning paradigm as well as strong local contextual modeling ability.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • IJCLCLP 2021 • Fu-An Chao, Tien-Hong Lo, Shi-Yan Weng, Shih-Hsuan Chiu, Yao-Ting Sung, Berlin Chen
This paper describes the NTNU ASR system participating in the Formosa Speech Recognition Challenge 2020 (FSR-2020) supported by the Formosa Speech in the Wild project (FSW).