Zobrazeno 1 - 10
of 2 003
pro vyhledávání: '"I. Fan"'
In this short paper we propose a data augmentation method for intent detection in zero-resource domains. Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many possible
Externí odkaz:
http://arxiv.org/abs/2410.01953
Autor:
Yu, Yu, Yang, Chao-Han Huck, Kolehmainen, Jari, Shivakumar, Prashanth G., Gu, Yile, Ryu, Sungho, Ren, Roger, Luo, Qi, Gourav, Aditya, Chen, I-Fan, Liu, Yi-Chieh, Dinh, Tuan, Gandhe, Ankur, Filimonov, Denis, Ghosh, Shalini, Stolcke, Andreas, Rastow, Ariya, Bulyko, Ivan
Publikováno v:
Proc. IEEE ASRU Workshop, Dec. 2023
We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high computati
Externí odkaz:
http://arxiv.org/abs/2309.15223
Differential privacy (DP) is one data protection avenue to safeguard user information used for training deep models by imposing noisy distortion on privacy data. Such a noise perturbation often results in a severe performance degradation in automatic
Externí odkaz:
http://arxiv.org/abs/2210.05614
Autor:
Dheram, Pranav, Ramakrishnan, Murugesan, Raju, Anirudh, Chen, I-Fan, King, Brian, Powell, Katherine, Saboowala, Melissa, Shetty, Karan, Stolcke, Andreas
Publikováno v:
Proc. Interspeech, Sept. 2022, pp. 1268-1272
As for other forms of AI, speech recognition has recently been examined with respect to performance disparities across different user cohorts. One approach to achieve fairness in speech recognition is to (1) identify speaker cohorts that suffer from
Externí odkaz:
http://arxiv.org/abs/2207.11345
Publikováno v:
International Journal of Emerging Markets, 2022, Vol. 18, Issue 11, pp. 4787-4818.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/IJOEM-12-2020-1522
Autor:
Lin, Kuan-Yin, Wang, Ching-Hsun, Su, Lian-Yi, Lin, I-Fan, Liu, Chia-Wei, Wu, Ping-Feng, Tsai, Wen-Chia, Chang, Chia-Ning, Hung, Miao-Chiu, Huang, Chien-Hsien, Chiu, Nan-Chang, Cheng, Ming-Fang, Hsieh, Szu-Min, Wang, Ning-Chi, Wang, Hsiao-Wei, Wong, Swee Siang, Lin, Po-Chang, Tsai, Ming-Han, Yang, Shun-Cheng, Lin, Hsiao-Chuan, Lee, Susan Shin-Jung, Chen, Yee-Chun, Wang, Fu-Der
Publikováno v:
In Journal of Microbiology, Immunology and Infection October 2024 57(5):669-684
Aminoglycoside utilization in elderly inpatients: Implications for renal health and adverse outcomes
Publikováno v:
In Archives of Gerontology and Geriatrics Plus September 2024 1(3)
In this paper, we propose an approach to quantitatively analyze impacts of different training label errors to RNN-T based ASR models. The result shows deletion errors are more harmful than substitution and insertion label errors in RNN-T training dat
Externí odkaz:
http://arxiv.org/abs/2112.00350
Autor:
Cheng, Meng-Hsuan, Kuo, Hsuan-Fu, Chang, Chia-Yuan, Chang, Jui-Chi, Liu, I.-Fan, Hsieh, Chong-Chao, Hsu, Chih-Hsin, Li, Chia-Yang, Wang, Shu-Chi, Chen, Yung-Hsiang, Chang, Chuang-Rung, Lee, Tsung-Ying, Liu, Yu-Ru, Huang, Chi-Yuan, Wu, Szu-Hui, Liu, Wei-Lun, Liu, Po-Len
Publikováno v:
In Biomedicine & Pharmacotherapy May 2024 174
Autor:
Okoli, George N., Righolt, Christiaan H., Zhang, Geng, Van Caeseele, Paul, Kuo, I fan, Alessi-Severini, Silvia, Mahmud, Salaheddin M.
Publikováno v:
In Vaccine 7 March 2024 42(7):1571-1581