no code implementations • RaPID (LREC) 2022 • Jiahong Yuan, Xingyu Cai, Kenneth Church
The result represents a relative error reduction of 14% over the baseline model trained without data augmentation.
no code implementations • NIDCP (LREC) 2022 • Juhong Zhan, Yue Jiang, Christopher Cieri, Mark Liberman, Jiahong Yuan, Yiya Chen, Odette Scharenborg
This paper describes our use of mixed incentives and the citizen science portal LanguageARC to prepare, collect and quality control a large corpus of object namings for the purpose of providing speech data to document the under-represented Guanzhong dialect of Chinese spoken in the Shaanxi province in the environs of Xi’an.
no code implementations • NAACL (BEA) 2022 • Lei Chen, Chenglin Jiang, Yiwei Gu, Yang Liu, Jiahong Yuan
Reduced form pronunciations are widely used by native English speakers, especially in casual conversations.
no code implementations • 27 Apr 2022 • Guangxu Xun, Mingbo Ma, Yuchen Bian, Xingyu Cai, Jiaji Huang, Renjie Zheng, Junkun Chen, Jiahong Yuan, Kenneth Church, Liang Huang
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency.
no code implementations • ICLR 2022 • Xingyu Cai, Jiahong Yuan, Yuchen Bian, Guangxu Xun, Jiaji Huang, Kenneth Church
Standard CTC computes a loss by aggregating over all possible alignment paths, that map the entire sequence to the entire label (full alignment).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 2 Aug 2021 • Jiahong Yuan, Xingyu Cai, Renjie Zheng, Liang Huang, Kenneth Church
Models of phonemes, broad phonetic classes, and syllables all significantly outperform the utterance model, demonstrating that phonetic units are helpful and should be incorporated in speech emotion recognition.
no code implementations • 2 Aug 2021 • Jiahong Yuan, Xingyu Cai, Dongji Gao, Renjie Zheng, Liang Huang, Kenneth Church
Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 2 Aug 2021 • Jiahong Yuan, Neville Ryant, Xingyu Cai, Kenneth Church, Mark Liberman
This study reports our efforts to improve automatic recognition of suprasegmentals by fine-tuning wav2vec 2. 0 with CTC, a method that has been successful in automatic speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • NAACL 2021 • Yuchen Bian, Jiaji Huang, Xingyu Cai, Jiahong Yuan, Kenneth Church
(What) We define and focus the study on redundancy matrices generated from pre-trained and fine-tuned BERT-base model for GLUE datasets.
1 code implementation • 29 Apr 2021 • Sibo Zhang, Jiahong Yuan, Miao Liao, Liangjun Zhang
With the advance of deep learning technology, automatic video generation from audio or text has become an emerging and promising research topic.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang
Simultaneous speech-to-speech translation is widely useful but extremely challenging, since it needs to generate target-language speech concurrently with the source-language speech, with only a few seconds delay.
no code implementations • 8 Oct 2020 • Trang Tran, Jiahong Yuan, Yang Liu, Mari Ostendorf
The differences in written text and conversational speech are substantial; previous parsers trained on treebanked text have given very poor results on spontaneous speech.
1 code implementation • 4 Oct 2020 • Lara Kassab, Alona Kryshchenko, Hanbaek Lyu, Denali Molitor, Deanna Needell, Elizaveta Rebrova, Jiahong Yuan
Further, we propose quantitative ways to measure the topic length and demonstrate the ability of S-NCPD (as well as its online variant) to discover short and long-lasting temporal topics in a controlled manner in semi-synthetic and real-world data including news headlines.