Search Results - "Liu, Andy T"

Adversarial Defense for Automatic Speaker Verification by Cascaded Self-Supervised Learning Models by Wu, Haibin, Li, Xu, Liu, Andy T., Wu, Zhiyong, Meng, Helen, Lee, Hung-yi

“…Automatic speaker verification (ASV) is one of the core technologies in biometric identification. With the ubiquitous usage of ASV systems in safety-critical…”
Get full text

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech by Liu, Andy T., Li, Shang-Wen, Lee, Hung-yi

“…We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches…”
Get full text

Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders by Liu, Andy T., Yang, Shu-wen, Chi, Po-Han, Hsu, Po-chun, Lee, Hung-yi

“…We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled…”
Get full text

Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning by Wu, Haibin, Li, Xu, Liu, Andy T., Wu, Zhiyong, Meng, Helen, Lee, Hung-Yi

“…Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech,…”
Get full text

Her2 promotes early dissemination of breast cancer by suppressing the p38-MK2-Hsp27 pathway that is targetable by Wip1 inhibition by Wang, Juan, Wang, Guanwen, Cheng, Dongmei, Huang, Shan, Chang, Antao, Tan, Xiaoming, Wang, Qiong, Zhao, Shaorong, Wu, Dan, Liu, Andy T., Yang, Shuang, Xiang, Rong, Sun, Peiqing

“…Cancer can metastasize from early lesions without detectable tumors. Despite extensive studies on metastasis in cancer cells from patients with detectable…”
Get full text

Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models by Meng, Yen, Chou, Yi-Hui, Liu, Andy T., Lee, Hung-yi

“…Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR. However, how pretraining data affects S3Ms'…”
Get full text

Parallel Synthesis for Autoregressive Speech Generation by Hsu, Po-chun, Liu, Da-rong, Liu, Andy T., Lee, Hung-yi

“…Autoregressive neural vocoders have achieved outstanding performance and are widely used in speech synthesis tasks such as text-to-speech and voice conversion…”
Get full text

A Large-Scale Evaluation of Speech Foundation Models by Yang, Shu-wen, Chang, Heng-Jui, Huang, Zili, Liu, Andy T., Lai, Cheng-I, Wu, Haibin, Shi, Jiatong, Chang, Xuankai, Tsai, Hsiang-Sheng, Huang, Wen-Chin, Feng, Tzu-hsun, Chi, Po-Han, Lin, Yist Y., Chuang, Yung-Sung, Huang, Tzu-Hsien, Tseng, Wei-Cheng, Lakhotia, Kushal, Li, Shang-Wen, Mohamed, Abdelrahman, Watanabe, Shinji, Lee, Hung-yi

“…The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal…”
Get full text

Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget by Liu, Andy T, Lin, Yi-Cheng, Wu, Haibin, Winkler, Stefan, Lee, Hung-yi

“…Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation…”
Get full text

Representation Learning of Structured Data for Medical Foundation Models by Dwivedi, Vijay Prakash, Schlegel, Viktor, Liu, Andy T, Nguyen, Thanh-Tung, Kashyap, Abhinav Ramesh, Wei, Jeng, Yin, Wei-Hsian, Winkler, Stefan, Tan, Robby T

“…Large Language Models (LLMs) have demonstrated remarkable performance across various domains, including healthcare. However, their ability to effectively…”
Get full text

MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues by Binici, Kuluhan, Kashyap, Abhinav Ramesh, Schlegel, Viktor, Liu, Andy T, Dwivedi, Vijay Prakash, Nguyen, Thanh-Tung, Gao, Xiaoxue, Chen, Nancy F, Winkler, Stefan

“…Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the…”
Get full text

uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization by Nagar, Aishik, Liu, Yutong, Liu, Andy T, Schlegel, Viktor, Dwivedi, Vijay Prakash, Kaliya-Perumal, Arun-Kumar, Kalanchiam, Guna Pratheep, Tang, Yili, Tan, Robby T

“…Medical abstractive summarization faces the challenge of balancing faithfulness and informativeness. Current methods often sacrifice key information for…”
Get full text

On the social bias of speech self-supervised models by Lin, Yi-Cheng, Lin, Tzu-Quan, Lin, Hsi-Che, Liu, Andy T, Lee, Hung-yi

“…Proc. Interspeech 2024, 4638-4642 Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes,…”
Get full text

Parallel Synthesis for Autoregressive Speech Generation by Hsu, Po-chun, Liu, Da-rong, Liu, Andy T, Lee, Hung-yi

“…Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive…”
Get full text

QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition by Liu, Andy T, Xiao, Wei, Zhu, Henghui, Zhang, Dejiao, Li, Shang-Wen, Arnold, Andrew

“…Recently, prompt-based learning for pre-trained language models has succeeded in few-shot Named Entity Recognition (NER) by exploiting prompts as task guidance…”
Get full text

Understanding Self-Attention of Self-Supervised Audio Transformers by Yang, Shu-wen, Liu, Andy T, Lee, Hung-yi

“…INTERSPEECH 2020 Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been…”
Get full text

Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning by Wu, Haibin, Liu, Andy T, Lee, Hung-yi

“…High-performance anti-spoofing models for automatic speaker verification (ASV), have been widely used to protect ASV by identifying and filtering spoofing…”
Get full text

Don't speak too fast: The impact of data bias on self-supervised speech models by Meng, Yen, Chou, Yi-Hui, Liu, Andy T, Lee, Hung-yi

“…Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR. However, how pre-training data affects S3Ms'…”
Get full text

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech by Liu, Andy T, Li, Shang-Wen, Lee, Hung-yi

“…IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, Vol. 29, 2021 We introduce a self-supervised speech pre-training method called TERA, which…”
Get full text

Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning by Wu, Haibin, Li, Xu, Liu, Andy T, Wu, Zhiyong, Meng, Helen, Lee, Hung-yi

“…Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech,…”
Get full text