Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Andy T Liu"'
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30:202-217
Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to defending ASV
Autor:
Po-Han Chi, Hung-yi Lee, Zili Huang, Ko-tik Lee, Shang-Wen Li, Tzu-hsien Huang, Guan-Ting Lin, Wei-Cheng Tseng, Jiatong Shi, Yung-Sung Chuang, Shinji Watanabe, Yist Y. Lin, Da-Rong Liu, Andy T. Liu, Shuyan Dong, Cheng-I Jeff Lai, Xuankai Chang, Shu-wen Yang, Abdelrahman Mohamed, Kushal Lakhotia
Publikováno v:
Interspeech 2021.
Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for va
Publikováno v:
ICASSP
Automatic speaker verification (ASV) is one of the core technologies in biometric identification. With the ubiquitous usage of ASV systems in safety-critical applications, more and more malicious attackers attempt to launch adversarial attacks at ASV
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5304ae10408be52811676aee6e60c3ad
We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction, autoregressive pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cac206a9eb2fed30138c98ecdde4dc7
http://arxiv.org/abs/2007.06028
http://arxiv.org/abs/2007.06028
Autor:
Dongmei Cheng, Dan Wu, Xiaoming Tan, Shan Huang, Peiqing Sun, Qiong Wang, Rong Xiang, Shaorong Zhao, Antao Chang, Juan Wang, Guanwen Wang, Shuang Yang, Andy T Liu
Publikováno v:
Oncogene
Cancer can metastasize from early lesions without detectable tumors. Despite extensive studies on metastasis in cancer cells from patients with detectable primary tumors, mechanisms for early metastatic dissemination are poorly understood. Her2 promo
Publikováno v:
INTERSPEECH
Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet. In this work, we present multiple strategies for the analysis of attention mechanisms i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5d485be7935fc348fa66c8466a5e11f
Publikováno v:
INTERSPEECH
High-performance anti-spoofing models for automatic speaker verification (ASV), have been widely used to protect ASV by identifying and filtering spoofing audio that is deliberately generated by text-to-speech, voice conversion, audio replay, etc. Ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02c35f15fc4236e7e84cdaf2991d791e
Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
Publikováno v:
ICASSP
We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef7f1f0ded410f5390643969124c5142
http://arxiv.org/abs/1910.12638
http://arxiv.org/abs/1910.12638
Publikováno v:
INTERSPEECH
We present an unsupervised end-to-end training scheme where we discover discrete subword units from speech without using any labels. The discrete subword units are learned under an ASR-TTS autoencoder reconstruction setting, where an ASR-Encoder is t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::222123ed749ab9fd73037df92bc2c87e
http://arxiv.org/abs/1905.11563
http://arxiv.org/abs/1905.11563