Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Wei-Ning Hsu"'
Autor:
Tu Anh Nguyen, Eugene Kharitonov, Jade Copet, Yossi Adi, Wei-Ning Hsu, Ali Elkahky, Paden Tomasello, Robin Algayres, Benoît Sagot, Abdelrahman Mohamed, Emmanuel Dupoux
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 250-266 (2023)
AbstractWe introduce dGSLM, the first “textless” model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attent
Externí odkaz:
https://doaj.org/article/66cdeee2fe844d3386d07e74704b7b6a
Autor:
Kushal Lakhotia, Eugene Kharitonov, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Benjamin Bolte, Tu-Anh Nguyen, Jade Copet, Alexei Baevski, Abdelrahman Mohamed, Emmanuel Dupoux
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1336-1354 (2021)
AbstractWe introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations a
Externí odkaz:
https://doaj.org/article/9f80ed410bfd419cbf7950582c5e58b4
Autor:
Wei-Ning Hsu, 許惟寗
101
14 species of Araliaceae plants grown in Taiwan were collected and studied on their antioxidant, anti-inflammation, anti adipogenesis and cytotoxic activities. The results indicated that the EtOH extracts of Eleutherococcus trifoliatus and S
14 species of Araliaceae plants grown in Taiwan were collected and studied on their antioxidant, anti-inflammation, anti adipogenesis and cytotoxic activities. The results indicated that the EtOH extracts of Eleutherococcus trifoliatus and S
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/54474722211379478022
Autor:
Wei-Ning Hsu, 徐瑋甯
99
A stereo vision system with two cameras is implemented in this thesis. Based on the stereo vision system, a distance measurement of a target object is investigated and applied to the Sprint event of FIRA HuroCup. In the distance measurement o
A stereo vision system with two cameras is implemented in this thesis. Based on the stereo vision system, a distance measurement of a target object is investigated and applied to the Sprint event of FIRA HuroCup. In the distance measurement o
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/67923035412745533165
Autor:
Wei-Ning Hsu, 許韋寧
99
Content addressable memory, a high-performance lookup engine in many systems, is widely used in communication network and cache system. However, owing to the mass and parallel comparison, the area overhead, power dissipation and reliability a
Content addressable memory, a high-performance lookup engine in many systems, is widely used in communication network and cache system. However, owing to the mass and parallel comparison, the area overhead, power dissipation and reliability a
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/83322171330714414018
Autor:
Wei-ning Hsu, 徐偉寧
97
The purpose of this thesis is to study the scaling behavior of the Manna sandpile model. First, we simulated the Manna model on a two-dimensional square lattice and a three-dimensional simple-cubic lattice. We found that the Manna model follo
The purpose of this thesis is to study the scaling behavior of the Manna sandpile model. First, we simulated the Manna model on a two-dimensional square lattice and a three-dimensional simple-cubic lattice. We found that the Manna model follo
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/59531030186467405466
Autor:
Ali Elkahky, Wei-Ning Hsu, Paden Tomasello, Tu-Anh Nguyen, Robin Algayres, Yossi Adi, Jade Copet, Emmanuel Dupoux, Abdelrahman Mohamed
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
We introduce the first unsupervised speech synthesis system based on a simple, yet effective recipe. The framework leverages recent work in unsupervised speech recognition as well as existing neural-based speech synthesis. Using only unlabeled speech
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a387b749a1137ac0e30e3b4ee0ff97a
http://arxiv.org/abs/2204.02524
http://arxiv.org/abs/2204.02524
Autor:
Ruslan Salakhutdinov, Wei-Ning Hsu, Yao-Hung Hubert Tsai, Benjamin Bolte, Abdelrahman Mohamed, Kushal Lakhotia
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 29:3451-3460
Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sou
Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of making sup
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e27919c1d41c028cae4979000f5dfa6