Search Results for author: Ryosuke Sawata

Found 5 papers, 1 papers with code

Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models

no code implementations12 Oct 2021 Ryosuke Sawata, Yosuke Kashiwagi, Shusuke Takahashi

In order to optimize the DNN-based SE model in terms of the character error rate (CER), which is one of the metric to evaluate the ASR system and generally non-differentiable, our method uses two DNNs: one for speech processing and one for mimicking the output CERs derived through an acoustic model (AM).

Automatic Speech Recognition Speech Enhancement +1

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.

Deep Clustering

All for One and One for All: Improving Music Separation by Bridging Networks

5 code implementations8 Oct 2020 Ryosuke Sawata, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji

This paper proposes several improvements for music separation with deep neural networks (DNNs), namely a multi-domain loss (MDL) and two combination schemes.

Music Source Separation

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