Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Chen, Berlin"'
Long document summarization poses a significant challenge in natural language processing due to input lengths that exceed the capacity of most state-of-the-art pre-trained language models. This study proposes a hierarchical framework that segments an
Externí odkaz:
http://arxiv.org/abs/2410.06520
Autor:
Wang, Chien-Chun, Chen, Li-Wei, Chou, Cheng-Kang, Lee, Hung-Shin, Chen, Berlin, Wang, Hsin-Min
While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mismatch stemming from unseen recording environments and conditions. To
Externí odkaz:
http://arxiv.org/abs/2409.12386
Second language (L2) learners can improve their pronunciation by imitating golden speech, especially when the speech that aligns with their respective speech characteristics. This study explores the hypothesis that learner-specific golden speech gene
Externí odkaz:
http://arxiv.org/abs/2409.07151
Automated speaking assessment in conversation tests (ASAC) aims to evaluate the overall speaking proficiency of an L2 (second-language) speaker in a setting where an interlocutor interacts with one or more candidates. Although prior ASAC approaches h
Externí odkaz:
http://arxiv.org/abs/2409.07064
End-to-end (E2E) automatic speech recognition (ASR) models have become standard practice for various commercial applications. However, in real-world scenarios, the long-tailed nature of word distribution often leads E2E ASR models to perform well on
Externí odkaz:
http://arxiv.org/abs/2409.06468
Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts forward a novel
Externí odkaz:
http://arxiv.org/abs/2409.01545
Autor:
Wu, Chung-Wen, Chen, Berlin
Automatic Speech Assessment (ASA) has seen notable advancements with the utilization of self-supervised features (SSL) in recent research. However, a key challenge in ASA lies in the imbalanced distribution of data, particularly evident in English te
Externí odkaz:
http://arxiv.org/abs/2406.10873
Autor:
Yan, Bi-Cheng, Chao, Wei-Cheng, Li, Jiun-Ting, Wang, Yi-Cheng, Wang, Hsin-Wei, Lin, Meng-Shin, Chen, Berlin
Automatic pronunciation assessment (APA) manages to evaluate the pronunciation proficiency of a second language (L2) learner in a target language. Existing efforts typically draw on regression models for proficiency score prediction, where the models
Externí odkaz:
http://arxiv.org/abs/2406.02859
Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar performance compar
Externí odkaz:
http://arxiv.org/abs/2404.07575
End-to-end automatic speech recognition (E2E ASR) systems often suffer from mistranscription of domain-specific phrases, such as named entities, sometimes leading to catastrophic failures in downstream tasks. A family of fast and lightweight named en
Externí odkaz:
http://arxiv.org/abs/2403.17645