activity
20212024
collaborators

8 papers

eess.AS2022

Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders

Futa Nakashima, Tomohiko Nakamura, Norihiro Takamune +2

In this paper, we propose a musical instrument sound synthesis (MISS) method based on a variational autoencoder (VAE) that has a hierarchy-inducing latent space for timbre. VAE-bas…

cs.SD2022

Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds

Masaya Kawamura, Tomohiko Nakamura, Daichi Kitamura +3

A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis. It allows us…

cs.SD2021

Speech Enhancement by Noise Self-Supervised Rank-Constrained Spatial Covariance Matrix Estimation via Independent Deeply Learned Matrix Analysis

Sota Misawa, Norihiro Takamune, Tomohiko Nakamura +4

Rank-constrained spatial covariance matrix estimation (RCSCME) is a method for the situation that the directional target speech and the diffuse noise are mixed. In conventional RCS…

cs.SD2021

Multichannel Audio Source Separation with Independent Deeply Learned Matrix Analysis Using Product of Source Models

Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune +4

Independent deeply learned matrix analysis (IDLMA) is one of the state-of-the-art multichannel audio source separation methods using the source power estimation based on deep neura…

cs.SD2021

Prior Distribution Design for Music Bleeding-Sound Reduction Based on Nonnegative Matrix Factorization

Yusaku Mizobuchi, Daichi Kitamura, Tomohiko Nakamura +3

When we place microphones close to a sound source near other sources in audio recording, the obtained audio signal includes undesired sound from the other sources, which is often c…

cs.SD2021

Independent Deeply Learned Tensor Analysis for Determined Audio Source Separation

Naoki Narisawa, Rintaro Ikeshita, Norihiro Takamune +4

We address the determined audio source separation problem in the time-frequency domain. In independent deeply learned matrix analysis (IDLMA), it is assumed that the inter-frequenc…