Prediction-error-based Adaptive SpecAugment for Fine-tuning the Masked Model on Audio Classification Tasks

Authors: Zhang, Xiao, Xing, Haoran, Song, Mingxue, Takeuchi, Daiki, Harada, Noboru, Makino, Shoji

Source: 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2024 Asia Pacific. :1-6 Dec, 2024

Relation: 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Refining Knowledge Transfer on Audio-Image Temporal Agreement for Audio-Text Cross Retrieval

Authors: Tsubaki, Shunsuke, Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Imoto, Keisuke

Source: 2024 32nd European Signal Processing Conference (EUSIPCO) European Signal Processing Conference (EUSIPCO), 2024 32nd. :71-75 Aug, 2024

Relation: 2024 32nd European Signal Processing Conference (EUSIPCO)

Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Source: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Engineering in Medicine and Biology Society (EMBC), 2024 46th Annual International Conference of the IEEE. :1-4 Jul, 2024

Relation: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Light Gated Multi Mini-Patch Extractor for Audio Classification

Authors: He, Bo, Zhang, Shiqi, Wang, Xianrui, Qiu, Zheng, Takeuchi, Daiki, Niizumi, Daisuke, Harada, Noboru, Makino, Shoji

Source: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) Acoustics, Speech, and Signal Processing Workshops (ICASSPW), 2024 IEEE International Conference on. :765-769 Apr, 2024

Relation: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

Unrestricted Global Phase Bias-Aware Single-Channel Speech Enhancement with Conformer-Based Metric Gan

Authors: Zhang, Shiqi, Qiu, Zheng, Takeuchi, Daiki, Harada, Noboru, Makino, Shoji

Source: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2024 - 2024 IEEE International Conference on. :1026-1030 Apr, 2024

Relation: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Yasuda, Masahiro, Tsubaki, Shunsuke, Imoto, Keisuke

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Multimedia, Computer Science - Sound, 68T07

Access URL: http://arxiv.org/abs/2406.02032

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound, 68T07

Access URL: http://arxiv.org/abs/2404.06095

First-Shot Anomaly Sound Detection for Machine Condition Monitoring: A Domain Generalization Baseline

Authors: Harada, Noboru, Niizumi, Daisuke, Ohishi, Yasunori, Takeuchi, Daiki, Yasuda, Masahiro

Source: 2023 31st European Signal Processing Conference (EUSIPCO) European Signal Processing Conference (EUSIPCO), 2023 31st. :191-195 Sep, 2023

Relation: 2023 31st European Signal Processing Conference (EUSIPCO)

Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Source: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2023 - 2023 IEEE International Conference on. :1-5 Jun, 2023

Relation: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Source: 2022 30th European Signal Processing Conference (EUSIPCO) European Signal Processing Conference (EUSIPCO), 2022 30th. :200-204 Aug, 2022

Relation: 2022 30th European Signal Processing Conference (EUSIPCO)

Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement

Authors: Takeuchi, Daiki, Ohishi, Yasunori, Niizumi, Daisuke, Harada, Noboru, Kashino, Kunio

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Sound

Access URL: http://arxiv.org/abs/2308.11923

Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound, 68T07

Access URL: http://arxiv.org/abs/2305.14079

Deep sound-field denoiser: optically-measured sound-field denoising using deep neural network

Authors: Ishikawa, Kenji, Takeuchi, Daiki, Harada, Noboru, Moriya, Takehiro

Subject Terms: Electrical Engineering and Systems Science - Signal Processing, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing, Electrical Engineering and Systems Science - Image and Video Processing, Physics - Optics

Access URL: http://arxiv.org/abs/2304.14923

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Source: 2021 International Joint Conference on Neural Networks (IJCNN) Neural Networks (IJCNN), 2021 International Joint Conference on. :1-8 Jul, 2021

Relation: 2021 International Joint Conference on Neural Networks (IJCNN)

Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Computer Science - Sound, 68T07

Access URL: http://arxiv.org/abs/2210.14648

Invertible DNN-Based Nonlinear Time-Frequency Transform for Speech Enhancement

Authors: Takeuchi, Daiki, Yatabe, Kohei, Koizumi, Yuma, Oikawa, Yasuhiro, Harada, Noboru

Source: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020 - 2020 IEEE International Conference on. :6644-6648 May, 2020

Relation: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Real-Time Speech Enhancement Using Equilibriated RNN

Authors: Takeuchi, Daiki, Yatabe, Kohei, Koizumi, Yuma, Oikawa, Yasuhiro, Harada, Noboru

Source: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020 - 2020 IEEE International Conference on. :851-855 May, 2020

Relation: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

ConceptBeam: Concept Driven Target Speech Extraction

Authors: Ohishi, Yasunori, Delcroix, Marc, Ochiai, Tsubasa, Araki, Shoko, Takeuchi, Daiki, Niizumi, Daisuke, Kimura, Akisato, Harada, Noboru, Kashino, Kunio

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Multimedia, Computer Science - Sound

Access URL: http://arxiv.org/abs/2207.11964

Introducing Auxiliary Text Query-modifier to Content-based Audio Retrieval

Authors: Takeuchi, Daiki, Ohishi, Yasunori, Niizumi, Daisuke, Harada, Noboru, Kashino, Kunio

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computation and Language, Computer Science - Information Retrieval, Computer Science - Machine Learning, Computer Science - Sound

Access URL: http://arxiv.org/abs/2207.09732

Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation

Authors: Niizumi, Daisuke, Takeuchi, Daiki, Ohishi, Yasunori, Harada, Noboru, Kashino, Kunio

Source: HEAR: Holistic Evaluation of Audio Representations (NeurIPS 2021 Competition) PMLR 166 (2022) 1-24

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound, 68T07

Access URL: http://arxiv.org/abs/2204.12260