Saijo (@kohei_1979) profile picture

Working on sound source separation.

Joined March 2021
Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)Photo by Saijo (@kohei_1979)
🔥Announcing the VoiceMOS Challenge 2026🔥 We are REVERTING BACK to the VoiceMOS Challenge, as there are still unsolved problems in the evaluation of speech itself 🤨 Pre-registration: forms.gle/L6YdkUf1PJdSSwLU7 Website: sites.google.com/view/voicem… See the tracks in the thread!
4
19
47
8,937
We are looking for a postdoctoral researcher in speech and audio processing, with a possible start in the Fall 2026 semester. If you are interested in working with us, please apply through the following form: forms.gle/gfENMMrRf1nmnTJeA
1
24
2
58
9,473
テックブログを公開しました。 「Scaling Speech AI」の下、1Bから3Bへと音声言語モデルをスケールさせた際のTTS性能へ影響を検証しました。 日本語特有の読みや表記揺れ、表現の広がりがみられるに加え、現状の課題についても整理しています。 日本語音声生成・SpeechLM・TTSに関心のある方はぜひご覧ください。 blog.dubguild.com/melte/llm-… 1B/3Bモデルの構築にあたって実施した、データ前処理・事前学習・事後学習の詳細も、今後順次公開していく予定です。 続報もお待ちいただければ幸いです。
45
8
173
32,609
先日博士課程を修了しました! 3年間多くの方々にお世話になりました。ありがとうございました。 修了記念に公聴会のスライドを公開しました: speakerdeck.com/kohei_1979/u… 今後も研究は続けていく予定なので、引き続きよろしくお願いいたします。
2
8
1
89
13,132
“Input-Adaptive Spectral Feature Compression by Sequence Modeling for Source Separation”, w/ @yoshipon0520, was accepted to IEEE TASLPRO! Introduced feature compression by seq. modeling + psychoacoustic inductive bias, outperforming band-splitting arxiv.org/abs/2602.08671
1
6
16
1,652
ICASSP 2025で発表した Task-aware Unified Source Separation のコードが出ました プロンプトで音源の種類を指定して、プロンプトの数だけ音源分離/抽出できます 色々な発展性があると思うので、ぜひ試してみてください! 最近出た FlexIO の基盤にもなってます arxiv.org/abs/2510.21485
We published the code of “Task-aware Unified Source Separation (TUSS)”, presented at ICASSP 2025! TUSS can separate arbitrary number of sounds just by specifying the desired source type(s). Code and Pre-trained Models: github.com/merlresearch/unif… Paper: arxiv.org/abs/2410.23987
5
1,053
We published the code of “Task-aware Unified Source Separation (TUSS)”, presented at ICASSP 2025! TUSS can separate arbitrary number of sounds just by specifying the desired source type(s). Code and Pre-trained Models: github.com/merlresearch/unif… Paper: arxiv.org/abs/2410.23987
1
4
1,351
TF-Locoformerのリポジトリに、EUSIPCO 2025で発表したNoPE (No Positional Encoding) バージョン追加しました 少し軽量になって、推論時の入力長に対する外挿性能が改善しました もし性能いい音声強調/音源分離モデル探していたら見てみてください🙌
Happy to see the TF-Locoformer repo got 100 stars! We added the NoPE variant. It performs better while being more efficient. Try it if you’re looking for a high-performing speech enhancement/separation model! Repo: github.com/merlresearch/tf-l… Paper: arxiv.org/abs/2504.19605
1
4
597
Happy to see the TF-Locoformer repo got 100 stars! We added the NoPE variant. It performs better while being more efficient. Try it if you’re looking for a high-performing speech enhancement/separation model! Repo: github.com/merlresearch/tf-l… Paper: arxiv.org/abs/2504.19605
1
3
834
Our ICASSP submission entitled "FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement" is now on arXiv! FlexIO can handle arbitrary numbers of microphones (inputs) and speakers (outputs) within a single model. arXiv: arxiv.org/abs/2510.21485
7
31
2,963
Yoshiki Masuyama, Kohei Saijo, Francesco Paissan, Jiangyu Han, Marc Delcroix, Ryo Aihara, Fran\c{c}ois G. Germain, Gordon Wichern, Jonathan Le Roux, "FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement," arxiv.org/abs/2510.21485
10
16
2,005
🚀 Join the ICASSP 2026 URGENT Challenge! Advance Universal, Robust & Generalizable Speech Enhancement. 🗣 Track 1: Universal Speech Enhancement 🎧 Track 2: Speech Quality Assessment 🔗 urgent-challenge.github.io/u… #ICASSP2026 #SpeechEnhancement #AI #AudioProcessing
7
2
13
3,753
End of the beginning! Thank you for the EMMA team and the JSALT organizers. The lectures and presentations on CSLP Youtube channel: youtube.com/@jhuclsp?si=oEus… My lecture slide for speech enhancement and separation: merl.com/publications/docs/T…
5
15
1,329
One paper got accepted to WASPAA 2025! “Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation” 📃Paper: arxiv.org/abs/2505.07631 We will publish the code and pre-trained models soon. See you in Tahoe!
5
29
1,493
Our paper "Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation" written by @kohei_1979 is accepted for IEEE WASPAA 2025! Congratulations🎉🎉🎉
7
36
2,022
I’ll be presenting a work on unified source separation model at #ICASSP tomorrow morning! The culmination of my 10-month internship at MERL🔥 📃 Task-Aware Unified Source Separation 📅 Apr. 10, 9:42-10:00am (oral) 📍MR1.02 (Audio Source Separation III)
3
17
1,560