AIConfPaper
← Search

Tsubasa Ochiai

26 accepted papers

2025

SoundBeam meets M2D: Target Sound Extraction with Audio Foundation Model

Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai, Daisuke Niizumi, Naohiro Tawara, Tomohiro Nakatani +1
ICASSP 2025accepted

Target sound extraction (TSE) consists of isolating a desired sound from a mixture of arbitrary sounds using clues to identify it. A TSE system requires solving two problems at once, identifying the target source and extracting the target signal from the mixture. For increased practicability, the sa…

Cited by 0Source ↗Scholar ↗
2025

TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models

Junyi Peng, Takanori Ashihara, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki +1
ICASSP 2025accepted

Self-supervised learning (SSL) models have significantly advanced speech processing tasks, and several benchmarks have been proposed to validate their effectiveness. However, previous benchmarks have primarily focused on single-speaker scenarios, with less exploration of target-speaker tasks in nois…

Cited by 0Source ↗Scholar ↗
2024

How Does End-To-End Speech Recognition Training Impact Speech Enhancement Artifacts?

Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki +1
ICASSP 2024accepted

Jointly training a speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end has been investigated as a way to mitigate the influence of processing distortion generated by single-channel SE on ASR. In this paper, we investigate the effect of such joint training on the sign…

Cited by 0Source ↗Scholar ↗
2024

Neural Network-Based Virtual Microphone Estimation with Virtual Microphone and Beamformer-Level Multi-Task Loss

Hanako Segawa, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Shoko Araki +2
ICASSP 2024accepted

Array processing performance depends on the number of microphones available. Virtual microphone estimation (VME) has been proposed to increase the number of microphone signals artificially. Neural network-based VME (NN-VME) trains an NN with a VM-level loss to predict a signal at a microphone locati…

Cited by 0Source ↗Scholar ↗
2024

Online Target Sound Extraction with Knowledge Distillation from Partially Non-Causal Teacher

Keigo Wakayama, Tsubasa Ochiai, Marc Delcroix, Masahiro Yasuda, Shoichiro Saito, Shoko Araki +1
ICASSP 2024accepted

Target Sound Extraction (TSE) is a technique for extracting sound events belonging to a target sound class in a mixture using a Deep Neural Network (DNN). Offline TSE that uses non-causal models has achieved high extraction performance. However, many applications require online processing. Simply co…

Cited by 10Source ↗Scholar ↗
2024

Target Speech Extraction with Pre-Trained Self-Supervised Learning Models

Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki, Jan Cernocký
ICASSP 2024accepted

Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target speaker in a mixture guided by enrollment utterances. We exp…

Cited by 0Source ↗Scholar ↗
2022

Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition

Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Naoyuki Kamo, Takafumi Moriya
ICASSP 2022accepted

The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement overlapping speech recognition. However, the SE front-end generates processing artifacts that can degrade the ASR performa…

Cited by 0Source ↗Scholar ↗
2021

Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation

Christoph Böddeker, Wangyou Zhang, Tomohiro Nakatani, Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix +3
ICASSP 2021accepted

Time-domain training criteria have proven to be very effective for the separation of single-channel non-reverberant speech mixtures. Likewise, mask-based beamforming has shown impressive performance in multi-channel reverberant speech enhancement and source separation. Here, we propose to combine ne…

Cited by 0Source ↗Scholar ↗
2021

Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain

Julio Wissing, Benedikt T. Boenninghoff, Dorothea Kolossa, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita +3
ICASSP 2021accepted

Estimating the positions of multiple speakers can be helpful for tasks like automatic speech recognition or speaker diarization. Both applications benefit from a known speaker position when, for instance, applying beamforming or assigning unique speaker identities. Recently, several approaches utili…

Cited by 0Source ↗Scholar ↗
2021

End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend

Wangyou Zhang, Christoph Böddeker, Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita +4
ICASSP 2021accepted

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both singlechannel and multichannel conditions. However, severe performance degradation is still observed in the reverberant and noisy scenarios, and there is still a large performan…

Cited by 0Source ↗Scholar ↗
2021

Neural Network-Based Virtual Microphone Estimator

Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki
ICASSP 2021accepted

Developing microphone array technologies for a small number of microphones is important due to the constraints of many devices. One direction to address this situation consists of virtually augmenting the number of microphone signals, e.g., based on several physical model assumptions. However, such…

Cited by 0Source ↗Scholar ↗
2021

Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition

Takafumi Moriya, Takanori Ashihara, Tomohiro Tanaka, Tsubasa Ochiai, Hiroshi Sato, Atsushi Ando +3
ICASSP 2021accepted

Recurrent neural network-transducer (RNN-T) is promising for building time-synchronous end-to-end automatic speech recognition (ASR) systems, in part because it does not need frame-wise alignment between input features and target labels in the training step. Although training without alignment is be…

Cited by 8Source ↗Scholar ↗
2021

Speaker Activity Driven Neural Speech Extraction

Marc Delcroix, Katerina Zmolíková, Tsubasa Ochiai, Keisuke Kinoshita, Tomohiro Nakatani
ICASSP 2021accepted

Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In thi…

Cited by 0Source ↗Scholar ↗
2020

A Dynamic Stream Weight Backprop Kalman Filter for Audiovisual Speaker Tracking

Christopher Schymura, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki +1
ICASSP 2020accepted

Audiovisual speaker tracking is an application that has been tackled by a wide range of classical approaches based on Gaussian filters, most notably the well-known Kalman filter. Recently, a specific Kalman filter implementation was proposed for this task, which incorporated dynamic stream weights t…

Cited by 0Source ↗Scholar ↗
2020

Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer

Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki
ICASSP 2020accepted

Recent studies have shown that acoustic beamforming using a microphone array plays an important role in the construction of high-performance automatic speech recognition (ASR) systems, especially for noisy and overlapping speech conditions. In parallel with the success of multichannel beamforming fo…

Cited by 0Source ↗Scholar ↗
2020

DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation

Tomohiro Nakatani, Riki Takahashi, Tsubasa Ochiai, Keisuke Kinoshita, Rintaro Ikeshita, Marc Delcroix +1
ICASSP 2020accepted

In this article, we investigate an integrated mask-based convolutional beamforming method for performing simultaneous denoising, dereverberation, and source separation. Conventionally, it is difficult for neural network-supported mask-based source separation to perform denoising and dereverberation…

Cited by 25Source ↗Scholar ↗
2020

Improving Noise Robust Automatic Speech Recognition with Single-Channel Time-Domain Enhancement Network

Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani
ICASSP 2020accepted

With the advent of deep learning, research on noise-robust automatic speech recognition (ASR) has progressed rapidly. However, ASR performance in noisy conditions of single-channel systems remains unsatisfactory. Indeed, most single-channel speech enhancement (SE) methods (denoising) have brought on…

Cited by 0Source ↗Scholar ↗
2020

Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam

Marc Delcroix, Tsubasa Ochiai, Katerina Zmolíková, Keisuke Kinoshita, Naohiro Tawara, Tomohiro Nakatani +1
ICASSP 2020accepted

Target speech extraction, which extracts a single target source in a mixture given clues about the target speaker, has attracted increasing attention. We have recently proposed SpeakerBeam, which exploits an adaptation utterance of the target speaker to extract his/her voice characteristics that are…

Cited by 152Source ↗Scholar ↗
2019

A Unified Framework for Neural Speech Separation and Extraction

Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Tomohiro Nakatani
ICASSP 2019accepted

The development of deep learning techniques has triggered the active investigation of neural network-based speech enhancement approaches. In particular, single-channel blind (uninformed) speech separation and speaker-aware (informed) speech extraction have received increased interest. Blind speech s…

Cited by 21Source ↗Scholar ↗
2019

Compact Network for Speakerbeam Target Speaker Extraction

Marc Delcroix, Katerina Zmolíková, Tsubasa Ochiai, Keisuke Kinoshita, Shoko Araki, Tomohiro Nakatani
ICASSP 2019accepted

Speech separation that separates a mixture of speech signals into each of its sources has been an active research topic for a long time and has seen recent progress with the advent of deep learning. A related problem is target speaker extraction, i.e. extraction of only speech of a target speaker ou…

Cited by 0Source ↗Scholar ↗
2018

Speaker Adaptation for Multichannel End-to-End Speech Recognition

Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri, Takaaki Hori, John R. Hershey
ICASSP 2018accepted

Recent work on multichannel end-to-end automatic speech recognition (ASR) has shown that multichannel speech enhancement and speech recognition functions can be integrated into a deep neural network (DNN)-based system, and promising experimental results have been shown using the CHiME-4 and AMI corp…

Cited by 0Source ↗Scholar ↗
2017

Automatic node selection for Deep Neural Networks using Group Lasso regularization

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
ICASSP 2017accepted

We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types of gLasso regularization, one for outgoing weight vectors and another for…

Cited by 0Source ↗Scholar ↗
2017

Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models

Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Taichi Asami, Shigeru Katagiri +1
ICASSP 2017accepted

Adapting acoustic models to speakers have shown to greatly improve performance for many tasks. Among the adaptation approaches, exploiting auxiliary features characterizing speakers or environments has received great attention because they allow rapid adaptation, i.e. adaptation with limited amount…

Cited by 0Source ↗Scholar ↗
2016

Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Hisashi Kawai, Shigeru Katagiri
ICASSP 2016accepted

Recently, a Hybrid DNN-HMM recognizer trained with the Speaker Adaptive Training (SAT) concept was successfully modified to a more effective speaker-adaptation-oriented recognizer whose DNN front-end adopted a Linear Transformation Network (LTN) Speaker Dependent (SD) module. However, the size of SD…

Cited by 0Source ↗Scholar ↗
2015

Speaker adaptive training for deep neural networks embedding linear transformation networks

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Shigeru Katagiri
ICASSP 2015accepted

Recently, a novel speaker adaptation method was proposed that applied the Speaker Adaptive Training (SAT) concept to a speech recognizer consisting of a Deep Neural Network (DNN) and a Hidden Markov Model (HMM), and its utility was demonstrated. This method implements the SAT scheme by allocating on…

Cited by 15Source ↗Scholar ↗