143 citations · 527 across the 38 of their papers we have counts for
26 papers · 1 filter
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…
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…
Mask scalar prediction for improving robust automatic speech recognition
Arun Narayanan, James Walker, Sankaran Panchapagesan +2
Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints a…
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…
SNRi Target Training for Joint Speech Enhancement and Recognition
Yuma Koizumi, Shigeki Karita, Arun Narayanan +2
Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is th…
DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement
Yuma Koizumi, Shigeki Karita, Scott Wisdom +4
Single-channel speech enhancement (SE) is an important task in speech processing. A widely used framework combines an analysis/synthesis filterbank with a mask prediction network,…
Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions
Yohei Kawaguchi, Keisuke Imoto, Yuma Koizumi +6
We present the task description and discussion on the results of the DCASE 2021 Challenge Task 2. In 2020, we organized an unsupervised anomalous sound detection (ASD) task, identi…
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…
Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval
Yuma Koizumi, Yasunori Ohishi, Daisuke Niizumi +2
The goal of audio captioning is to translate input audio into its description using natural language. One of the problems in audio captioning is the lack of training data due to th…
Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning
Daiki Takeuchi, Yuma Koizumi, Yasunori Ohishi +2
The system we used for Task 6 (Automated Audio Captioning)of the Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge combines three elements, namely, d…
A Transformer-based Audio Captioning Model with Keyword Estimation
Yuma Koizumi, Ryo Masumura, Kyosuke Nishida +2
One of the problems with automated audio captioning (AAC) is the indeterminacy in word selection corresponding to the audio event/scene. Since one acoustic event/scene can be descr…
The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation
Yuma Koizumi, Daiki Takeuchi, Yasunori Ohishi +2
This technical report describes the system participating to the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge, Task 6: automated audio captionin…
Listen to What You Want: Neural Network-based Universal Sound Selector
Tsubasa Ochiai, Marc Delcroix, Yuma Koizumi +3
Being able to control the acoustic events (AEs) to which we want to listen would allow the development of more controllable hearable devices. This paper addresses the AE sound sele…
Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring
Yuma Koizumi, Yohei Kawaguchi, Keisuke Imoto +8
In this paper, we present the task description and discuss the results of the DCASE 2020 Challenge Task 2: Unsupervised Detection of Anomalous Sounds for Machine Condition Monitori…
Sound Event Localization based on Sound Intensity Vector Refined By DNN-Based Denoising and Source Separation
Masahiro Yasuda, Yuma Koizumi, Shoichiro Saito +2
We propose a direction-of-arrival (DOA) estimation method for Sound Event Localization and Detection (SELD). Direct estimation of DOA using a deep neural network (DNN), i.e. comple…
Stable Training of DNN for Speech Enhancement based on Perceptually-Motivated Black-Box Cost Function
Masaki Kawanaka, Yuma Koizumi, Ryoichi Miyazaki +1
Improving subjective sound quality of enhanced signals is one of the most important missions in speech enhancement. For evaluating the subjective quality, several methods related t…
Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention
Yuma Koizumi, Kohei Yatabe, Marc Delcroix +2
This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly fro…
Real-time speech enhancement using equilibriated RNN
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi +2
We propose a speech enhancement method using a causal deep neural network~(DNN) for real-time applications. DNN has been widely used for estimating a time-frequency~(T-F) mask whic…
Phase reconstruction based on recurrent phase unwrapping with deep neural networks
Yoshiki Masuyama, Kohei Yatabe, Yuma Koizumi +2
Phase reconstruction, which estimates phase from a given amplitude spectrogram, is an active research field in acoustical signal processing with many applications including audio s…
Invertible DNN-based nonlinear time-frequency transform for speech enhancement
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi +2
We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enh…
DOA Estimation by DNN-based Denoising and Dereverberation from Sound Intensity Vector
Masahiro Yasuda, Yuma Koizumi, Luca Mazzon +2
We propose a direction of arrival (DOA) estimation method that combines sound-intensity vector (IV)-based DOA estimation and DNN-based denoising and dereverberation. Since the accu…
First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation
Luca Mazzon, Yuma Koizumi, Masahiro Yasuda +1
In this paper, we propose a novel data augmentation method for training neural networks for Direction of Arrival (DOA) estimation. This method focuses on expanding the representati…
ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection
Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu +2
This paper introduces a new dataset called "ToyADMOS" designed for anomaly detection in machine operating sounds (ADMOS). To the best our knowledge, no large-scale datasets are ava…
Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds
Yuma Koizumi, Shoichiro Saito, Masataka Yamaguchi +2
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of th…