Takuya Hasumi

15 papers A 3Misc 2Journal 7Unranked 3
YearRankTypeTitle / Venue / Authors
2025 Misc conf
Aligned Contrastive Learning for Text-to-Music Retrieval.
ICASSP
Tatsuya Komatsu, Hokuto Munakata, Takuya Hasumi, Yusuke Fujita
2025 A conf
BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing.
INTERSPEECH
Masaya Kawamura, Takuya Hasumi, Yuma Shirahata, Ryuichi Yamamoto
2025 J jnl
BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing.
CoRR
Masaya Kawamura, Takuya Hasumi, Yuma Shirahata, Ryuichi Yamamoto
2025 J jnl
DnR-nonverbal: Cinematic Audio Source Separation Dataset Containing Non-Verbal Sounds.
CoRR
Takuya Hasumi, Yusuke Fujita
2025 A conf
DnR-nonverbal: Cinematic Audio Source Separation DatasetContaining Non-Verbal Sounds.
INTERSPEECH
Takuya Hasumi, Yusuke Fujita
2025 Misc conf
Music Tagging with Classifier Group Chains.
ICASSP
Takuya Hasumi, Tatsuya Komatsu, Yusuke Fujita
2025 J jnl
Music Tagging with Classifier Group Chains.
CoRR
Takuya Hasumi, Tatsuya Komatsu, Yusuke Fujita
2024 A conf
LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning.
INTERSPEECH
Masaya Kawamura, Ryuichi Yamamoto, Yuma Shirahata, Takuya Hasumi, Kentaro Tachibana
2024 J jnl
LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning.
CoRR
Masaya Kawamura, Ryuichi Yamamoto, Yuma Shirahata, Takuya Hasumi, Kentaro Tachibana
2023 J jnl
PoP-IDLMA: Product-of-Prior Independent Deeply Learned Matrix Analysis for Multichannel Music Source Separation.
IEEE ACM Trans. Audio Speech Lang. Process.
Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo
2021 — conf
Empirical Bayesian Independent Deeply Learned Matrix Analysis For Multichannel Audio Source Separation.
EUSIPCO
Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo
2021 J jnl
Empirical Bayesian Independent Deeply Learned Matrix Analysis For Multichannel Audio Source Separation.
CoRR
Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo
2021 — conf
Multichannel Audio Source Separation with Independent Deeply Learned Matrix Analysis Using Product of Source Models.
APSIPA ASC
Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo
2021 J jnl
Multichannel Audio Source Separation with Independent Deeply Learned Matrix Analysis Using Product of Source Models.
CoRR
Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo
2020 — conf
Investigation of Network Architecture for Single-Channel End-to-End Denoising.
EUSIPCO
Takuya Hasumi, Tetsunori Kobayashi, Tetsuji Ogawa