Saijo

Working on sound source separation.

[Wen-Chin Huang @unilightwf]

🔥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: https://t.co/3mb3Dpxm1D
Website: https://t.co/N5DS7ryrtx

See the tracks in the thread!

[Shinji Watanabe @shinjiw_at_cmu]

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: https://t.co/ssjinOn6LW

[DubGuild @DubGuild]

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。
https://t.co/XfkfBCQXfg

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。

[Saijo @kohei_1979]

@jeonchangbin49 Thanks Chang-Bin!

[Saijo @kohei_1979]

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： https://t.co/TgPykAS7ZM

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。

[Saijo @kohei_1979]

@Muramasa_2 ありがとうございます！
またお会いした際はよろしくお願いします🙌

[Saijo @kohei_1979]

Codes have been published!

https://t.co/iKVVpUt2Sk

[Saijo @kohei_1979]

“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

https://t.co/r7rT2XBoW7

[arXiv Sound @ArxivSound]

Kohei Saijo, Yoshiaki Bando, "Input-Adaptive Spectral Feature Compression by Sequence Modeling for Source Separation," https://t.co/kjShdJEsWa

[Saijo @kohei_1979]

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
https://t.co/7z21HmCSF4

[Saijo @kohei_1979]

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: https://t.co/k8qWc3JGMJ

Paper: https://t.co/ox0Kk3nE8T

[Saijo @kohei_1979]

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: https://t.co/k8qWc3JGMJ

Paper: https://t.co/ox0Kk3nE8T

[Saijo @kohei_1979]

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🙌

[Saijo @kohei_1979]

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: https://t.co/4EoVdtZwsD

Paper: https://t.co/29RoS88MAi

[Saijo @kohei_1979]

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: https://t.co/4EoVdtZwsD

Paper: https://t.co/29RoS88MAi

[まっすー @ymas0315]

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: https://t.co/KN4FcXNZGc

[arXiv Sound @ArxivSound]

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," https://t.co/F2thUbXSuU

[Chenda @chenda54]

🚀 Join the ICASSP 2026 URGENT Challenge! Advance Universal, Robust & Generalizable Speech Enhancement.
🗣 Track 1: Universal Speech Enhancement
🎧 Track 2: Speech Quality Assessment

🔗 https://t.co/bZ3edVhIGM

#ICASSP2026 #SpeechEnhancement #AI #AudioProcessing

[まっすー @ymas0315]

End of the beginning! Thank you for the EMMA team and the JSALT organizers.

The lectures and presentations on CSLP Youtube channel: https://t.co/5c6XnkT1bc
My lecture slide for speech enhancement and separation: https://t.co/9rzUuhB7aJ

[Saijo @kohei_1979]

少し先ですが、以下の論文を発表予定です

よろしくお願いします！

Interspeech: https://t.co/WjfOGgk6IF

EUSIPCO: https://t.co/29RoS88MAi

WASPAA: https://t.co/hUDhpUXVVW

[Saijo @kohei_1979]

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: https://t.co/hUDhpUXVVW

We will publish the code and pre-trained models soon.

See you in Tahoe!

[Yoshiaki Bando @yoshipon0520]

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🎉🎉🎉