Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Mao, Tingzhi"'
Publikováno v:
Proc. Interspeech 2024, 247-251 (2024)
The transducer model trained based on sequence-level criterion requires a lot of memory due to the generation of the large probability matrix. We proposed a lightweight transducer model based on frame-level criterion, which uses the results of the CT
Externí odkaz:
http://arxiv.org/abs/2409.13698
We report our NTU-AISG Text-to-speech (TTS) entry systems for the Blizzard Challenge 2020 in this paper. There are two TTS tasks in this year's challenge, one is a Mandarin TTS task, the other is a Shanghai dialect TTS task. We have participated both
Externí odkaz:
http://arxiv.org/abs/2010.11489
Autor:
Mao, Tingzhi, Khassanov, Yerbolat, Pham, Van Tung, Xu, Haihua, Huang, Hao, Wumaier, Aishan, Chng, Eng Siong
Automatic speech recognition (ASR) for under-represented named-entity (UR-NE) is challenging due to such named-entities (NE) have insufficient instances and poor contextual coverage in the training data to learn reliable estimates and representations
Externí odkaz:
http://arxiv.org/abs/2010.12143
In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words correspond to
Externí odkaz:
http://arxiv.org/abs/2005.08742
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.