7 citations · 29 across the 18 of their papers we have counts for
18 papers
Self-supervised learning method using multiple sampling strategies for general-purpose audio representation
Ibuki Kuroyanagi, Tatsuya Komatsu
We propose a self-supervised learning method using multiple sampling strategies to obtain general-purpose audio representation. Multiple sampling strategies are used in the propose…
Neural Diarization with Non-autoregressive Intermediate Attractors
Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler +2
End-to-end neural diarization (EEND) with encoder-decoder-based attractors (EDA) is a promising method to handle the whole speaker diarization problem simultaneously with a single…
How Information on Acoustic Scenes and Sound Events Mutually Benefits Event Detection and Scene Classification Tasks
Keisuke Imoto, Yuka Komatsu, Shunsuke Tsubaki +1
Acoustic scene classification (ASC) and sound event detection (SED) are fundamental tasks in environmental sound analysis, and many methods based on deep learning have been propose…
Better Intermediates Improve CTC Inference
Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee +3
This paper proposes a method for improved CTC inference with searched intermediates and multi-pass conditioning. The paper first formulates self-conditioned CTC as a probabilistic…
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR
Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita +2
This paper proposes InterAug: a novel training method for CTC-based ASR using augmented intermediate representations for conditioning. The proposed method exploits the conditioning…
Non-Autoregressive ASR with Self-Conditioned Folded Encoders
Tatsuya Komatsu
This paper proposes CTC-based non-autoregressive ASR with self-conditioned folded encoders. The proposed method realizes non-autoregressive ASR with fewer parameters by folding the…
Acoustic Event Detection with Classifier Chains
Tatsuya Komatsu, Shinji Watanabe, Koichi Miyazaki +1
This paper proposes acoustic event detection (AED) with classifier chains, a new classifier based on the probabilistic chain rule. The proposed AED with classifier chains consists…
MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
Jin Sakuma, Tatsuya Komatsu, Robin Scheibler
We propose multi-layer perceptron (MLP)-based architectures suitable for variable length input. MLP-based architectures, recently proposed for image classification, can only be use…
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Yosuke Higuchi, Nanxin Chen, Yuya Fujita +6
Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to aut…
Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers
Yusuke Kida, Tatsuya Komatsu, Masahito Togami
This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long…
Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions
Jumon Nozaki, Tatsuya Komatsu
This paper proposes a method to relax the conditional independence assumption of connectionist temporal classification (CTC)-based automatic speech recognition (ASR) models. We tra…
Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation
Tsubasa Takahashi, Shun Takagi, Hajime Ono +1
This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints. We often build a VAE with an appropriate prior distri…
Consistency-aware multi-channel speech enhancement using deep neural networks
Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
This paper proposes a deep neural network (DNN)-based multi-channel speech enhancement system in which a DNN is trained to maximize the quality of the enhanced time-domain signal.…
Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function
Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu +1
In this paper, we propose a multi-channel speech source separation with a deep neural network (DNN) which is trained under the condition that no clean signal is available. As an al…
Overview of Tasks and Investigation of Subjective Evaluation Methods in Environmental Sound Synthesis and Conversion
Yuki Okamoto, Keisuke Imoto, Tatsuya Komatsu +4
Synthesizing and converting environmental sounds have the potential for many applications such as supporting movie and game production, data augmentation for sound event detection…
Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming
Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
In this paper, we propose two mask-based beamforming methods using a deep neural network (DNN) trained by multichannel loss functions. Beamforming technique using time-frequency (T…
Bayesian Non-Parametric Multi-Source Modelling Based Determined Blind Source Separation
Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
This paper proposes a determined blind source separation method using Bayesian non-parametric modelling of sources. Conventionally source signals are separated from a given set of…
Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning
Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
This paper proposes an effective modelling of sound event spectra with a hidden data-size-imbalance, for improved Acoustic Event Detection (AED). The proposed method models each ev…