Zobrazeno 1 - 10 of 15 pro vyhledávání: '"Takanori Ashihara"'
1
Akademický článek
Unveiling the Linguistic Capabilities of a Self-Supervised Speech Model Through Cross-Lingual Benchmark and Layer- Wise Similarity Analysis
Autor: Takanori Ashihara, Marc Delcroix, Yusuke Ijima, Makio Kashino
Publikováno v: IEEE Access, Vol 12, Pp 98835-98855 (2024)
Self-supervised learning (SSL), an unsupervised representation learning technique, has received widespread attention across various modalities. Speech, with its inherent complexity encompassing acoustic (e.g., speaker, phoneme, and paralinguistic cue
Externí odkaz: https://doaj.org/article/e4b647188a4c4606a0dc899c95f100cf
Zobrazit plný text záznamu
4
Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
Autor: Takanori Ashihara, Takafumi Moriya, Kohei Matsuura, Tomohiro Tanaka
Self-supervised learning (SSL) has been dramatically successful not only in monolingual but also in cross-lingual settings. However, since the two settings have been studied individually in general, there has been little research focusing on how effe
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9607f09fe7d7b77892eb7909b01750c0
Zobrazit plný text záznamu
9
Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition
Autor: Takafumi Moriya, Mana Ihori, Takanori Ashihara, Shota Orihashi, Akihiko Takashima, Naoki Makishima, Tomohiro Tanaka, Ryo Masumura
Publikováno v: Interspeech 2021.
We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder networks, whi
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d68a5d355a6400b6de15b5cceb9ca5aa
https://doi.org/10.21437/interspeech.2021-1992
Zobrazit plný text záznamu
10
Speech Emotion Recognition Based on Listener Adaptive Models
Autor: Tomoki Toda, Ryo Masumura, Takanori Ashihara, Hiroshi Sato, Ando Atsushi, Yusuke Ijima, Takafumi Moriya
Publikováno v: ICASSP
This paper presents a novel speech emotion recognition scheme that can deal with the individuality of emotion perception. Most conventional methods directly model the majority decision of multiple listener’s perceived emotions. However, emotion per
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::26d4a8493a783ebe2ea523a82e6ed0e3
https://doi.org/10.1109/icassp39728.2021.9414698
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje