Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Wan, Xucheng"'
Contextualized ASR models have been demonstrated to effectively improve the recognition accuracy of uncommon phrases when a predefined phrase list is available. However, these models often struggle with bilingual settings, which are prevalent in code
Externí odkaz:
http://arxiv.org/abs/2408.10524
Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this challenge
Externí odkaz:
http://arxiv.org/abs/2406.09950
Autor:
Mu, Bingshen, Li, Yangze, Shao, Qijie, Wei, Kun, Wan, Xucheng, Zheng, Naijun, Zhou, Huan, Xie, Lei
Despite notable advancements in automatic speech recognition (ASR), performance tends to degrade when faced with adverse conditions. Generative error correction (GER) leverages the exceptional text comprehension capabilities of large language models
Externí odkaz:
http://arxiv.org/abs/2405.03152
Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single scale. In t
Externí odkaz:
http://arxiv.org/abs/2404.05466
Autor:
Chen, Peikun, Yu, Fan, Lian, Yuhao, Xue, Hongfei, Wan, Xucheng, Zheng, Naijun, Zhou, Huan, Xie, Lei
Mixture-of-experts based models, which use language experts to extract language-specific representations effectively, have been well applied in code-switching automatic speech recognition. However, there is still substantial space to improve as simil
Externí odkaz:
http://arxiv.org/abs/2310.02629
Target speech extraction (TSE) systems are designed to extract target speech from a multi-talker mixture. The popular training objective for most prior TSE networks is to enhance reconstruction performance of extracted speech waveform. However, it ha
Externí odkaz:
http://arxiv.org/abs/2303.05023
As a practical alternative of speech separation, target speaker extraction (TSE) aims to extract the speech from the desired speaker using additional speaker cue extracted from the speaker. Its main challenge lies in how to properly extract and lever
Externí odkaz:
http://arxiv.org/abs/2301.06277
To address the monaural speech enhancement problem, numerous research studies have been conducted to enhance speech via operations either in time-domain on the inner-domain learned from the speech mixture or in time--frequency domain on the fixed ful
Externí odkaz:
http://arxiv.org/abs/2209.11905
Overlapped speech detection (OSD) is critical for speech applications in scenario of multi-party conversion. Despite numerous research efforts and progresses, comparing with speech activity detection (VAD), OSD remains an open challenge and its overa
Externí odkaz:
http://arxiv.org/abs/2209.11906
Although state-of-the-art parallel WaveNet has addressed the issue of real-time waveform generation, there remains problems. Firstly, due to the noisy input signal of the model, there is still a gap between the quality of generated and natural wavefo
Externí odkaz:
http://arxiv.org/abs/1812.02339