no code implementations • ROCLING 2021 • Ke-Han Lu, Kuan-Yu Chen
In this paper, we proposed a BERT-based dimensional semantic analyzer, which is designed by incorporating with word-level information.
no code implementations • 30 Dec 2023 • Chih-Kai Yang, Kuan-Po Huang, Ke-Han Lu, Chun-Yi Kuan, Chi-Yuan Hsiao, Hung-Yi Lee
This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, on three code-switched corpora.
1 code implementation • 18 Sep 2023 • Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang, Chi-Yuan Hsiao, Chun-Yi Kuan, Haibin Wu, Siddhant Arora, Kai-Wei Chang, Jiatong Shi, Yifan Peng, Roshan Sharma, Shinji Watanabe, Bhiksha Ramakrishnan, Shady Shehata, Hung-Yi Lee
To achieve comprehensive coverage of diverse speech tasks and harness instruction tuning, we invite the community to collaborate and contribute, facilitating the dynamic growth of the benchmark.
1 code implementation • 18 Sep 2023 • Yi-Wei Wang, Ke-Han Lu, Kuan-Yu Chen
In addition, we implement and compare several classic and representative methods, showing the recent research progress in revising speech recognition results.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 12 Oct 2022 • Ke-Han Lu, Kuan-Yu Chen
Non-autoregressive automatic speech recognition (ASR) modeling has received increasing attention recently because of its fast decoding speed and superior performance.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 24 Jun 2021 • Ke-Han Lu, Bo-Han Fang, Kuan-Yu Chen
In this paper, inspired by the successes of visionlanguage pre-trained models and the benefits from training with adversarial attacks, we present a novel transformerbased cross-modal fusion modeling by incorporating the both notions for VQA challenge 2021.