30 citations · 115 across the 34 of their papers we have counts for
34 papers
Versatile Time-Frequency Representations Realized by Convex Penalty on Magnitude Spectrogram
Keidai Arai, Koki Yamada, Kohei Yatabe
Sparse time-frequency (T-F) representations have been an important research topic for more than several decades. Among them, optimization-based methods (in particular, extensions o…
Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune +2
In this paper, we propose algorithms for handling non-integer strides in sampling-frequency-independent (SFI) convolutional and transposed convolutional layers. The SFI layers have…
LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus
Yuma Koizumi, Heiga Zen, Shigeki Karita +7
This paper introduces a new speech dataset called ``LibriTTS-R'' designed for text-to-speech (TTS) use. It is derived by applying speech restoration to the LibriTTS corpus, which c…
Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations
Yuma Koizumi, Heiga Zen, Shigeki Karita +7
Speech restoration (SR) is a task of converting degraded speech signals into high-quality ones. In this study, we propose a robust SR model called Miipher, and apply Miipher to a n…
Online Phase Reconstruction via DNN-based Phase Differences Estimation
Yoshiki Masuyama, Kohei Yatabe, Kento Nagatomo +1
This paper presents a two-stage online phase reconstruction framework using causal deep neural networks (DNNs). Phase reconstruction is a task of recovering phase of the short-time…
WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration
Yuma Koizumi, Kohei Yatabe, Heiga Zen +1
Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characteriz…
Measuring pitch extractors' response to frequency-modulated multi-component signals
Hideki Kawahara, Kohei Yatabe, Ken-Ichi Sakakibara +3
This article focuses on the research tool for investigating the fundamental frequencies of voiced sounds. We introduce an objective and informative measurement method of pitch extr…
An objective test tool for pitch extractors' response attributes
Hideki Kawahara, Kohei Yatabe, Ken-Ichi Sakakibara +3
We propose an objective measurement method for pitch extractors' responses to frequency-modulated signals. It enables us to evaluate different pitch extractors with unified criteri…
SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping
Yuma Koizumi, Heiga Zen, Kohei Yatabe +2
Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, w…
Wearable SELD dataset: Dataset for sound event localization and detection using wearable devices around head
Kento Nagatomo, Masahiro Yasuda, Kohei Yatabe +2
Sound event localization and detection (SELD) is a combined task of identifying the sound event and its direction. Deep neural networks (DNNs) are utilized to associate them with t…
APPLADE: Adjustable Plug-and-play Audio Declipper Combining DNN with Sparse Optimization
Tomoro Tanaka, Kohei Yatabe, Masahiro Yasuda +1
In this paper, we propose an audio declipping method that takes advantages of both sparse optimization and deep learning. Since sparsity-based audio declipping methods have been de…
Safeguarding test signals for acoustic measurement using arbitrary sounds
Hideki Kawahara, Kohei Yatabe
We propose a simple method to measure acoustic responses using any sounds by converting them suitable for measurement. This method enables us to use music pieces for measuring acou…
Design of Tight Minimum-Sidelobe Windows by Riemannian Newton's Method
Daichi Kitahara, Kohei Yatabe
The short-time Fourier transform (STFT), or the discrete Gabor transform (DGT), has been extensively used in signal analysis and processing. Their properties are characterized by a…
Objective measurement of pitch extractors' responses to frequency modulated sounds and two reference pitch extraction methods for analyzing voice pitch responses to auditory stimulation
Hideki Kawahara, Kohei Yatabe, Ken-Ichi Sakakibara +3
We propose an objective measurement method for pitch extractors' responses to frequency-modulated signals. The method simultaneously measures the linear and the non-linear time-inv…
Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method
Koichi Saito, Tomohiko Nakamura, Kohei Yatabe +2
Audio source separation is often used as preprocessing of various applications, and one of its ultimate goals is to construct a single versatile model capable of dealing with the v…
Sparse time-frequency representation via atomic norm minimization
Tsubasa Kusano, Kohei Yatabe, Yasuhiro Oikawa
Nonstationary signals are commonly analyzed and processed in the time-frequency (T-F) domain that is obtained by the discrete Gabor transform (DGT). The T-F representation obtained…
Mixture of orthogonal sequences made from extended time-stretched pulses enables measurement of involuntary voice fundamental frequency response to pitch perturbation
Hideki Kawahara, Toshie Matsui, Kohei Yatabe +4
Auditory feedback plays an essential role in the regulation of the fundamental frequency of voiced sounds. The fundamental frequency also responds to auditory stimulation other tha…
Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech
Takuya Fujimura, Yuma Koizumi, Kohei Yatabe +1
Deep neural network (DNN)-based speech enhancement ordinarily requires clean speech signals as the training target. However, collecting clean signals is very costly because they mu…
Cascaded all-pass filters with randomized center frequencies and phase polarity for acoustic and speech measurement and data augmentation
Hideki Kawahara, Kohei Yatabe
We introduce a new member of TSP (Time Stretched Pulse) for acoustic and speech measurement infrastructure, based on a simple all-pass filter and systematic randomization. This new…
Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling
Yoshiki Masuyama, Yoshiaki Bando, Kohei Yatabe +3
Detecting sound source objects within visual observation is important for autonomous robots to comprehend surrounding environments. Since sounding objects have a large variety with…
Consistent Independent Low-Rank Matrix Analysis for Determined Blind Source Separation
Daichi Kitamura, Kohei Yatabe
Independent low-rank matrix analysis (ILRMA) is the state-of-the-art algorithm for blind source separation (BSS) in the determined situation (the number of microphones is greater t…
Gamma Boltzmann Machine for Simultaneously Modeling Linear- and Log-amplitude Spectra
Toru Nakashika, Kohei Yatabe
In audio applications, one of the most important representations of audio signals is the amplitude spectrogram. It is utilized in many machine-learning-based information processing…
Consistent ICA: Determined BSS meets spectrogram consistency
Kohei Yatabe
Multichannel audio blind source separation (BSS) in the determined situation (the number of microphones is equal to that of the sources), or determined BSS, is performed by multich…
Determined BSS based on time-frequency masking and its application to harmonic vector analysis
Kohei Yatabe, Daichi Kitamura
This paper proposes harmonic vector analysis (HVA) based on a general algorithmic framework of audio blind source separation (BSS) that is also presented in this paper. BSS for a c…