Zobrazeno 1 - 10 of 41 pro vyhledávání: '"Xuankai Chang"'
4
End-to-End Multi-Speaker ASR with Independent Vector Analysis
Autor: Robin Scheibler, Wangyou Zhang, Xuankai Chang, Shinji Watanabe, Yanmin Qian
Publikováno v: 2022 IEEE Spoken Language Technology Workshop (SLT).
We develop an end-to-end system for multi-channel, multi-speaker automatic speech recognition. We propose a frontend for joint source separation and dereverberation based on the independent vector analysis (IVA) paradigm. It uses the fast and stable
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c11f55da0cf345da0edf10e296a1ea03
https://doi.org/10.1109/slt54892.2023.10023037
Zobrazit plný text záznamu
5
Superb @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning
Autor: Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh, Shu-wen Yang, Tzu-Quan Lin, Jiatong Shi, Kai-Wei Chang, Zili Huang, Haibin Wu, Xuankai Chang, Shinji Watanabe, Abdelrahman Mohamed, Shang-Wen Li, Hung-yi Lee
Publikováno v: 2022 IEEE Spoken Language Technology Workshop (SLT).
We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge builds upon the SUPERB benchmark and implements metrics to measure the com
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d1269adcfa0535af6d3fa2635806560
https://doi.org/10.1109/slt54892.2023.10022770
Zobrazit plný text záznamu
6
A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding
Autor: Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask: which (if an
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4c4867f2a63f8631a97664ab3e404e1
http://arxiv.org/abs/2211.05869
Zobrazit plný text záznamu
7
End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation
Autor: Xuankai Chang, Takashi Maekaku, Yuya Fujita, Shinji Watanabe
Publikováno v: Interspeech 2022.
This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS). Compared wit
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a04b1728d8d58d6cbc72474e715f2509
https://doi.org/10.21437/interspeech.2022-10839
Zobrazit plný text záznamu
9
Two-Pass Low Latency End-to-End Spoken Language Understanding
Autor: Siddhant Arora, Siddharth Dalmia, Xuankai Chang, Brian Yan, Alan W Black, Shinji Watanabe
End-to-end (E2E) models are becoming increasingly popular for spoken language understanding (SLU) systems and are beginning to achieve competitive performance to pipeline-based approaches. However, recent work has shown that these models struggle to
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2cc314f4b249f8973f91fe13ed30f9da
http://arxiv.org/abs/2207.06670
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje