Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Li, Jinyu"'
Autor:
Wu, Jian, Gaur, Yashesh, Chen, Zhuo, Zhou, Long, Zhu, Yimeng, Wang, Tianrui, Li, Jinyu, Liu, Shujie, Ren, Bo, Liu, Linquan, Wu, Yu
Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::99eb9d516394e3811b6f509b7c7fc3d0
http://arxiv.org/abs/2307.03917
http://arxiv.org/abs/2307.03917
Recent end-to-end automatic speech recognition (ASR) systems often utilize a Transformer-based acoustic encoder that generates embedding at a high frame rate. However, this design is inefficient, particularly for long speech signals due to the quadra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc3855bab09f4bc7b8c3107b081d3b7f
http://arxiv.org/abs/2306.16009
http://arxiv.org/abs/2306.16009
The integration of Language Models (LMs) has proven to be an effective way to address domain shifts in speech recognition. However, these approaches usually require a significant amount of target domain text data for the training of LMs. Different fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38090c0a55d370bec08810bda39f5985
http://arxiv.org/abs/2306.16007
http://arxiv.org/abs/2306.16007
Autor:
Yang, Muqiao, Kanda, Naoyuki, Wang, Xiaofei, Wu, Jian, Sivasankaran, Sunit, Chen, Zhuo, Li, Jinyu, Yoshioka, Takuya
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human t
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable improvement in
Autor:
Wei, Kun, Zhou, Long, Zhang, Ziqiang, Chen, Liping, Liu, Shujie, He, Lei, Li, Jinyu, Wei, Furu
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Direct speech-to-speech translation (S2ST) is an attractive research topic with many advantages compared to cascaded S2ST. However, direct S2ST suffers from the data scarcity problem because the corpora from speech of the source language to speech of
Autor:
Wang, Tianrui, Zhou, Long, Zhang, Ziqiang, Wu, Yu, Liu, Shujie, Gaur, Yashesh, Chen, Zhuo, Li, Jinyu, Wei, Furu
Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::071e31d93750cf76e2c5f8f576a56722
http://arxiv.org/abs/2305.16107
http://arxiv.org/abs/2305.16107
In order to deal with the sparse and unstructured raw point clouds, LiDAR based 3D object detection research mostly focuses on designing dedicated local point aggregators for fine-grained geometrical modeling. In this paper, we revisit the local poin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b43fd58fad4296e69f9a127c9b00c245
http://arxiv.org/abs/2305.04925
http://arxiv.org/abs/2305.04925
Publikováno v:
IEEE Transactions on Power Delivery. 37:1068-1077
Air-core reactors used in filters are significant equipment in HVDC converter stations. They are among the most serious noise sources under the action of multi-frequency magnetic forces. The vibration and noise characteristics of air-core reactors ar
Autor:
Gaur, Yashesh, Kibre, Nick, Xue, Jian, Shu, Kangyuan, Wang, Yuhui, Alphanso, Issac, Li, Jinyu, Gong, Yifan
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT).
Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However, humans prefer a written form output. To bridge this gap, ASR systems usually employ Inverse Text Normalization (ITN). In previous works, Weighted Finite State