88 citations · 197 across the 76 of their papers we have counts for
7 papers · 2 filters
Incremental Text-to-Speech Synthesis Using Pseudo Lookahead with Large Pretrained Language Model
Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
This letter presents an incremental text-to-speech (TTS) method that performs synthesis in small linguistic units while maintaining the naturalness of output speech. Incremental TT…
Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix Factorization Based on Multivariate Complex Sub-Gaussian Distribution
Keigo Kamo, Yuki Kubo, Norihiro Takamune +4
In this paper, we address a statistical model extension of multichannel nonnegative matrix factorization (MNMF) for blind source separation, and we propose a new parameter update a…
Convergence-guaranteed Independent Positive Semidefinite Tensor Analysis Based on Student's t Distribution
Tatsuki Kondo, Kanta Fukushige, Norihiro Takamune +4
In this paper, we address a blind source separation (BSS) problem and propose a new extended framework of independent positive semidefinite tensor analysis (IPSDTA). IPSDTA is a st…
Lifter Training and Sub-band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials
Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi +1
In this paper, we propose computationally efficient and high-quality methods for statistical voice conversion (VC) with direct waveform modification based on spectral differentials…
Regularized Fast Multichannel Nonnegative Matrix Factorization with ILRMA-based Prior Distribution of Joint-Diagonalization Process
Keigo Kamo, Yuki Kubo, Norihiro Takamune +4
In this paper, we address a convolutive blind source separation (BSS) problem and propose a new extended framework of FastMNMF by introducing prior information for joint diagonaliz…
Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform
Tomohiko Nakamura, Hiroshi Saruwatari
We propose a time-domain audio source separation method using down-sampling (DS) and up-sampling (US) layers based on a discrete wavelet transform (DWT). The proposed method is bas…