Zobrazeno 1 - 10
of 209
pro vyhledávání: '"Ma Mingbo"'
Publikováno v:
Nanotechnology Reviews, Vol 10, Iss 1, Pp 1592-1623 (2021)
Vertically aligned carbon nanotube (VACNT) materials is a promising candidate in different fields. The intrinsic performance of VACNTs, such as a large specific surface area, high conductivity, and especially its vertical conductive channel, stands o
Externí odkaz:
https://doaj.org/article/324d5cb1e5f14c56babcf04b630e1f1f
Autor:
Anastassiou, Philip, Tang, Zhenyu, Peng, Kainan, Jia, Dongya, Li, Jiaxin, Tu, Ming, Wang, Yuping, Wang, Yuxuan, Ma, Mingbo
We present VoiceShop, a novel speech-to-speech framework that can modify multiple attributes of speech, such as age, gender, accent, and speech style, in a single forward pass while preserving the input speaker's timbre. Previous works have been cons
Externí odkaz:
http://arxiv.org/abs/2404.06674
Autor:
Lam, Max W. Y., Tian, Qiao, Li, Tang, Yin, Zongyu, Feng, Siyuan, Tu, Ming, Ji, Yuliang, Xia, Rui, Ma, Mingbo, Song, Xuchen, Chen, Jitong, Wang, Yuping, Wang, Yuxuan
Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requi
Externí odkaz:
http://arxiv.org/abs/2305.15719
Autor:
Jia, Dongya, Tian, Qiao, Peng, Kainan, Li, Jiaxin, Chen, Yuanzhe, Ma, Mingbo, Wang, Yuping, Wang, Yuxuan
The goal of accent conversion (AC) is to convert the accent of speech into the target accent while preserving the content and speaker identity. AC enables a variety of applications, such as language learning, speech content creation, and data augment
Externí odkaz:
http://arxiv.org/abs/2212.05751
Autor:
Xun, Guangxu, Ma, Mingbo, Bian, Yuchen, Cai, Xingyu, Huang, Jiaji, Zheng, Renjie, Chen, Junkun, Yuan, Jiahong, Church, Kenneth, Huang, Liang
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major limitations: (a) it is a fixed p
Externí odkaz:
http://arxiv.org/abs/2204.12672
Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation. However, all the above tasks are in the direction of speech understanding, but for the
Externí odkaz:
http://arxiv.org/abs/2203.09690
Autor:
Wang, Shixin, Guo, Yuan, Du, Xianfeng, Liang, Zhongshuai, Ma, Mingbo, Xie, Yuehong, You, Wenzhi, Meng, Yi, Li, Dong, Liu, Mingxia, Liu, Yifan
Publikováno v:
In Chemical Engineering Journal 15 August 2024 494
Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate these issu
Externí odkaz:
http://arxiv.org/abs/2106.06636
Recently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a unified representation for bo
Externí odkaz:
http://arxiv.org/abs/2102.05766
End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the pipeline.
Externí odkaz:
http://arxiv.org/abs/2010.11445