Zobrazeno 1 - 10
of 1 104
pro vyhledávání: '"SUZUKI, Masayuki"'
Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data for EC are collected by automatically pairing a large set of ASR hypothe
Externí odkaz:
http://arxiv.org/abs/2407.13300
Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems. However, existing works only transfer a single representation of LLM (
Externí odkaz:
http://arxiv.org/abs/2309.04031
Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring. However, whether or how they can benefit competitive, near state-of-the-art ASR systems remains unexplored. In this study, we i
Externí odkaz:
http://arxiv.org/abs/2204.00212
Autor:
Cui, Xiaodong, Saon, George, Nagano, Tohru, Suzuki, Masayuki, Fukuda, Takashi, Kingsbury, Brian, Kurata, Gakuto
We introduce two techniques, length perturbation and n-best based label smoothing, to improve generalization of deep neural network (DNN) acoustic models for automatic speech recognition (ASR). Length perturbation is a data augmentation algorithm tha
Externí odkaz:
http://arxiv.org/abs/2203.15176
Publikováno v:
In Optics Communications 15 June 2024 561
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Optics Communications 1 July 2023 538
Autor:
Thomas, Samuel, Suzuki, Masayuki, Huang, Yinghui, Kurata, Gakuto, Tuske, Zoltan, Saon, George, Kingsbury, Brian, Picheny, Michael, Dibert, Tom, Kaiser-Schatzlein, Alice, Samko, Bern
With recent advances in deep learning, considerable attention has been given to achieving automatic speech recognition performance close to human performance on tasks like conversational telephone speech (CTS) recognition. In this paper we evaluate t
Externí odkaz:
http://arxiv.org/abs/1904.13258
Publikováno v:
In Materials Science & Engineering A 4 March 2021 806
Autor:
Matsuzono, Kosuke, Furuya, Kohei, Mashiko, Takafumi, Ozawa, Tadashi, Miura, Kumiko, Suzuki, Masayuki, Ozawa, Misato, Shimazaki, Haruo, Koide, Reiji, Tanaka, Ryota, Fujimoto, Shigeru
Publikováno v:
In Journal of the Neurological Sciences 15 August 2020 415