Výsledky vyhledávání - "Park, Joonyong"

Report

Autor: Chan, David M., Corona, Rodolfo, Park, Joonyong, Cho, Cheol Jun, Bai, Yutong, Darrell, Trevor

With the introduction of transformer-based models for vision and language tasks, such as LLaVA and Chameleon, there has been renewed interest in the discrete tokenized representation of images. These models often treat image patches as discrete token

Externí odkaz: http://arxiv.org/abs/2411.05001

Zobrazit plný text záznamu

Report

A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora

Autor: Onda, Kentaro, Park, Joonyong, Minematsu, Nobuaki, Saito, Daisuke

We propose a method of simulating the human process of foreign accentuation using Generative Spoken Language Model (GSLM) only with native speech corpora. When one listens to spoken words of a foreign language and repeats them, the repeated speech is

Externí odkaz: http://arxiv.org/abs/2407.11370

Zobrazit plný text záznamu

Report

Do learned speech symbols follow Zipf's law?

Autor: Takamichi, Shinnosuke, Maeda, Hiroki, Park, Joonyong, Saito, Daisuke, Saruwatari, Hiroshi

In this study, we investigate whether speech symbols, learned through deep learning, follow Zipf's law, akin to natural language symbols. Zipf's law is an empirical law that delineates the frequency distribution of words, forming fundamentals for sta

Externí odkaz: http://arxiv.org/abs/2309.09690

Zobrazit plný text záznamu

Report

How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics

Autor: Park, Joonyong, Takamichi, Shinnosuke, Nakamura, Tomohiko, Seki, Kentaro, Xin, Detai, Saruwatari, Hiroshi

We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. Since GSLM facilitates textless spoken language pro

Externí odkaz: http://arxiv.org/abs/2306.00697

Zobrazit plný text záznamu