Gebruikersprofielen voor Jinchuan Tian

Jinchuan Tian

Language Technologies Institute, Carnegie Mellon University
Geverifieerd e-mailadres voor andrew.cmu.edu
Geciteerd door 440

Study on mechanism of improving efficiency of permanent-magnet small ball-end magnetorheological polishing by increasing magnetorheological fluid temperature

J Tian, M Chen, H Liu, B Qin, J Cheng, Y Sun - Scientific Reports, 2022 - nature.com
Permanent-magnet small ball-end magnetorheological polishing method can be used to
polish the small part with complex structure. However, the material removal rate of this method …

Lae: Language-aware encoder for monolingual and multilingual asr

J Tian, J Yu, C Zhang, C Weng, Y Zou, D Yu - arXiv preprint arXiv …, 2022 - arxiv.org
Jinchuan Tian1,2, Jianwei Yu2,3, Chunlei Zhang2, Chao Weng2… This work is done when
Jinchuan Tian was an intern in … Tian, J. Tao, YT Yeung, and L. Deng, “Reducing language …

Improving Mandarin end-to-end speech recognition with word N-gram language model

J Tian, J Yu, C Weng, Y Zou… - IEEE Signal Processing …, 2022 - ieeexplore.ieee.org
Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has
been shown that incorporating external language models (LMs) into the decoding can further …

Uniaudio: An audio foundation model toward universal audio generation

D Yang, J Tian, X Tan, R Huang, S Liu, X Chang… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language models (LLM) have demonstrated the capability to handle a variety of
generative tasks. This paper presents the UniAudio system, which, unlike prior task-specific …

Hifi-codec: Group-residual vector quantization for high fidelity audio codec

D Yang, S Liu, R Huang, J Tian, C Weng… - arXiv preprint arXiv …, 2023 - arxiv.org
Audio codec models are widely used in audio communication as a crucial technique for
compressing audio into discrete representations. Nowadays, audio codec models are …

Consistent training and decoding for end-to-end speech recognition using lattice-free MMI

J Tian, J Yu, C Weng, SX Zhang, D Su… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Recently, End-to-End (E2E) frameworks have achieved remarkable results on various Automatic
Speech Recognition (ASR) tasks. However, Lattice-Free Maximum Mutual Information (…

Reproducing whisper-style training using an open-source toolkit and publicly available data

Y Peng, J Tian, B Yan, D Berrebbi… - 2023 IEEE Automatic …, 2023 - ieeexplore.ieee.org
Pre-training speech models on large volumes of data has achieved remarkable success.
OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech …

A novel specialized material removal rate model considering the synergistic effect of dynamic pressure and shear stress for the permanent-magnet small ball-end …

J Tian, H Liu, J Cheng, M Chen, B Qin, C Ma… - Journal of Manufacturing …, 2023 - Elsevier
Jinchuan Tian]. Polishing simulation, polishing experiment and data analysis were performed
by [Jinchuan Tian… by [Jian Cheng] and [Jinchuan Tian]. All authors commented on previous …

[HTML][HTML] A novel method of water bath heating assisted small ball-end magnetorheological polishing for hemispherical shell resonators

T Jinchuan, C Mingjun, J Cheng, LIU Henan - Chinese Journal of …, 2023 - Elsevier
Hemispherical shell resonator (HSR) is the core component of hemispherical resonator gyro.
It is a ψ-shaped small-bore complex component with minimum curvature radius less than 3 …

Microstructure and wear characterization of carbon nanotubes (CNTs) reinforced aluminum matrix nanocomposites manufactured using selective laser melting

T Yu, J Liu, Y He, J Tian, M Chen, Y Wang - Wear, 2021 - Elsevier
Aluminum matrix composites are attractive in aerospace and automobile industry due to its
low density, high strength and high corrosion resistance. Additive manufacturing methods …