Search Results for author: Keitaro Tanaka

Found 5 papers, 0 papers with code

Audio-Visual Speech Enhancement With Selective Off-Screen Speech Extraction

no code implementations10 Jun 2023 Tomoya Yoshinaga, Keitaro Tanaka, Shigeo Morishima

This paper describes an audio-visual speech enhancement (AV-SE) method that estimates from noisy input audio a mixture of the speech of the speaker appearing in an input video (on-screen target speech) and of a selected speaker not appearing in the video (off-screen target speech).

Computational Efficiency Speech Enhancement +1

Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning

no code implementations23 May 2023 Sara Kashiwagi, Keitaro Tanaka, Qi Feng, Shigeo Morishima

This paper presents a novel metric learning approach to address the performance gap between normal and silent speech in visual speech recognition (VSR).

Metric Learning speech-recognition +1

Memory Efficient Diffusion Probabilistic Models via Patch-based Generation

no code implementations14 Apr 2023 Shinei Arakawa, Hideki Tsunashima, Daichi Horita, Keitaro Tanaka, Shigeo Morishima

Second, we propose Global Content Conditioning (GCC) to ensure patches have coherent content when concatenated together.

Manifold-Aware Deep Clustering: Maximizing Angles between Embedding Vectors Based on Regular Simplex

no code implementations4 Jun 2021 Keitaro Tanaka, Ryosuke Sawata, Shusuke Takahashi

This paper presents a new deep clustering (DC) method called manifold-aware DC (M-DC) that can enhance hyperspace utilization more effectively than the original DC.

Clustering Deep Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.