• Publications
  • Influence
Determined Blind Source Separation Unifying Independent Vector Analysis and Nonnegative Matrix Factorization
TLDR
This paper addresses the determined blind source separation problem and proposes a new effective method unifying independent vector analysis (IVA) and nonnegative matrix factorization (NMF). Expand
  • 172
  • 32
The fundamental limitation of frequency domain blind source separation for convolutive mixtures of speech
TLDR
We show that it is not good to be constrained by the condition T>P, where T is the frame length of the DFT and P is the length of room impulse responses. Expand
  • 335
  • 17
Blind Source Separation Combining Independent Component Analysis and Beamforming
TLDR
We describe a new method of blind source separation (BSS) on a microphone array combining subband independent component analysis (ICA) and beamforming. Expand
  • 197
  • 17
  • PDF
Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
TLDR
A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Expand
  • 122
  • 8
  • PDF
Blind source separation based on a fast-convergence algorithm combining ICA and beamforming
TLDR
We propose a new algorithm for blind source separation (BSS), in which independent component analysis (ICA) and beamforming are combined to resolve the slow-convergence problem through optimization in ICA. Expand
  • 192
  • 7
Blind Spatial Subtraction Array for Speech Enhancement in Noisy Environment
TLDR
We propose a new blind spatial subtraction array (BSSA) consisting of a noise estimator based on independent component analysis (ICA) for efficient speech enhancement. Expand
  • 108
  • 7
GMM-based voice conversion applied to emotional speech synthesis
TLDR
EUROSPEECH2003: 8th European Conference on Speech Communication and Technology, September 1-4, 2003, Geneva, Switzerland. Expand
  • 89
  • 6
  • PDF
Training algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis
TLDR
This paper proposes a novel training algorithm for high-quality Deep Neural Network (DNN)-based speech synthesis that uses an Anti-Spoofing Verification (ASV) as an additional constraint in the acoustic model training. Expand
  • 33
  • 5
  • PDF
Blind Separation of Speech by Fixed-Point ICA with Source Adaptive Negentropy Approximation
TLDR
This paper presents a study on the blind separation of a convoluted mixture of speech signals using Frequency Domain Independent Component Analysis (FDICA) algorithm based on the negentropy maximization of Time Frequency Series of Speech (TFSS). Expand
  • 24
  • 5
  • PDF