SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling

no code implementations • 1 Jul 2024 • Hiroshi Sato, Takafumi Moriya, Masato Mimura, Shota Horiguchi, Tsubasa Ochiai, Takanori Ashihara, Atsushi Ando, Kentaro Shinayama, Marc Delcroix

Real-time target speaker extraction (TSE) is intended to extract the desired speaker's voice from the observed mixture of multiple speakers in a streaming manner.

Target Speaker Extraction

Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss

no code implementations • 24 May 2023 • Hiroshi Sato, Ryo Masumura, Tsubasa Ochiai, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Kentaro Shinayama, Saki Mizuno, Mana Ihori, Tomohiro Tanaka, Nobukatsu Hojo

In this work, we propose a new SE training criterion that minimizes the distance between clean and enhanced signals in the feature representation of the SSL model to alleviate the mismatch.

Self-Supervised Learning Speech Enhancement