Search Results for author: Masahito Togami

Found 7 papers, 1 papers with code

Sound Source Separation Using Latent Variational Block-Wise Disentanglement

no code implementations8 Feb 2024 Karim Helwani, Masahito Togami, Paris Smaragdis, Michael M. Goodwin

In this paper, we present a hybrid classical digital signal processing/deep neural network (DSP/DNN) approach to source separation (SS) highlighting the theoretical link between variational autoencoder and classical approaches to SS.

Disentanglement

Refinement of Direction of Arrival Estimators by Majorization-Minimization Optimization on the Array Manifold

1 code implementation2 Jun 2021 Robin Scheibler, Masahito Togami

We propose a generalized formulation of direction of arrival estimation that includes many existing methods such as steered response power, subspace, coherent and incoherent, as well as speech sparsity-based methods.

Direction of Arrival Estimation

Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers

no code implementations21 Apr 2021 Yusuke Kida, Tatsuya Komatsu, Masahito Togami

The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into utterance-wise pairs of speech and text.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Joint Dereverberation and Separation with Iterative Source Steering

no code implementations12 Feb 2021 Taishi Nakashima, Robin Scheibler, Masahito Togami, Nobutaka Ono

In this case, we manage to reduce the number of matrix inversion to only one per iteration and source.

blind source separation

Surrogate Source Model Learning for Determined Source Separation

no code implementations11 Nov 2020 Robin Scheibler, Masahito Togami

We find that the learnt approximate surrogate generalizes well on mixtures of three and four speakers without any modification.

Speech Separation

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