Takuya Higuchi

54 papers A* 2A 10C 4Misc 13Journal 17Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Which Data Matter? Embedding-Based Data Selection for Speech Recognition. CoRR Zakaria Aldeneh, Skyler Seto, Maureen de Seyssel, Jie Chi, Zijin Gu, Takuya Higuchi, Jee-weon Jung, Shinji Watanabe, David Grangier, Barry-John Theobald, Tatiana Likhomanenko
2025	A*	`conf`	A Variational Framework for Improving Naturalness in Generative Spoken Language Models. ICML Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh, Ahmed Hussen Abdelaziz, Alexander Rudnicky
2025	J	`jnl`	A Variational Framework for Improving Naturalness in Generative Spoken Language Models. CoRR Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh, Ahmed Hussen Abdelaziz, Alexander Rudnicky
2025	A	`conf`	DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective. INTERSPEECH Hyung-Gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko, Oggi Rudovic, Takuya Higuchi, Li-Wei Chen, Shinji Watanabe, Ahmed Hussen Abdelaziz
2025	J	`jnl`	DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective. CoRR Hyung-Gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko, Oggi Rudovic, Takuya Higuchi, Li-Wei Chen, Shinji Watanabe, Ahmed Hussen Abdelaziz
2025	Misc	`conf`	Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models. ICASSP Li-Wei Chen, Takuya Higuchi, He Bai, Ahmed Hussen Abdelaziz, Shinji Watanabe, Alexander Rudnicky, Tatiana Likhomanenko, Barry-John Theobald, Zakaria Aldeneh
2025	—	`conf`	Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations. WASPAA Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden
2025	Misc	`conf`	Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels. ICASSP Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Li-Wei Chen, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald
2025	Misc	`conf`	Towards Automatic Assessment of Self-Supervised Speech Models using Rank. ICASSP Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi, Barry-John Theobald, Tatiana Likhomanenko
2024	A	`conf`	Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? INTERSPEECH Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald
2024	J	`jnl`	Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? CoRR Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald
2024	A	`conf`	ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models. INTERSPEECH Jee-weon Jung, Wangyou Zhang, Jiatong Shi, Zakaria Aldeneh, Takuya Higuchi, Alex Gichamba, Barry-John Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe
2024	J	`jnl`	ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models. CoRR Jee-weon Jung, Wangyou Zhang, Jiatong Shi, Zakaria Aldeneh, Takuya Higuchi, Barry-John Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe
2024	J	`jnl`	Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models. CoRR Li-Wei Chen, Takuya Higuchi, He Bai, Ahmed Hussen Abdelaziz, Alexander Rudnicky, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald, Zakaria Aldeneh
2024	—	`conf`	Multichannel Voice Trigger Detection Based on Transform-Average-Concatenate. ICASSP Workshops Takuya Higuchi, Avamarie Brueggeman, Masood Delfarah, Stephen Shum
2024	J	`jnl`	Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations. CoRR Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden
2024	J	`jnl`	Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels. CoRR Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Li-Wei Chen, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Tatiana Likhomanenko, Barry-John Theobald
2024	J	`jnl`	Towards Automatic Assessment of Self-Supervised Speech Models using Rank. CoRR Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi, Barry-John Theobald, Tatiana Likhomanenko
2023	J	`jnl`	Does Single-channel Speech Enhancement Improve Keyword Spotting Accuracy? A Case Study. CoRR Avamarie Brueggeman, Takuya Higuchi, Masood Delfarah, Stephen Shum, Vineet Garg
2023	J	`jnl`	Multichannel Voice Trigger Detection Based on Transform-average-concatenate. CoRR Takuya Higuchi, Avamarie Brueggeman, Masood Delfarah, Stephen Shum
2022	A	`conf`	Improving Voice Trigger Detection with Metric Learning. INTERSPEECH Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed H. Tewfik
2022	J	`jnl`	Improving Voice Trigger Detection with Metric Learning. CoRR Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed H. Tewfik
2021	Misc	`conf`	Dynamic Curriculum Learning via Data Parameters for Noise Robust Keyword Spotting. ICASSP Takuya Higuchi, Shreyas Saxena, Mehrez Souden, Tien Dung Tran, Masood Delfarah, Chandra Dhir
2021	J	`jnl`	Dynamic curriculum learning via data parameters for noise robust keyword spotting. CoRR Takuya Higuchi, Shreyas Saxena, Mehrez Souden, Tien Dung Tran, Masood Delfarah, Chandra Dhir
2021	C	`conf`	Multi-Task Learning with Cross Attention for Keyword Spotting. ASRU Takuya Higuchi, Anmol Gupta, Chandra Dhir
2021	J	`jnl`	Multi-task Learning with Cross Attention for Keyword Spotting. CoRR Takuya Higuchi, Anmol Gupta, Chandra Dhir
2020	A	`conf`	Stacked 1D Convolutional Networks for End-to-End Small Footprint Voice Trigger Detection. INTERSPEECH Takuya Higuchi, Mohammad Ghasemzadeh, Kisun You, Chandra Dhir
2020	J	`jnl`	Stacked 1D convolutional networks for end-to-end small footprint voice trigger detection. CoRR Takuya Higuchi, Mohammad Ghasemzadeh, Kisun You, Chandra Dhir
2018	Misc	`conf`	Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation. ICASSP Lukas Drude, Takuya Higuchi, Keisuke Kinoshita, Tomohiro Nakatani, Reinhold Haeb-Umbach
2018	Misc	`conf`	Frame-by-Frame Closed-Form Update for Mask-Based Adaptive MVDR Beamforming. ICASSP Takuya Higuchi, Keisuke Kinoshita, Nobutaka Ito, Shigeki Karita, Tomohiro Nakatani
2018	J	`jnl`	Nonnegative Matrix Factorization With Basis Clustering Using Cepstral Distance Regularization. IEEE ACM Trans. Audio Speech Lang. Process. Hirokazu Kameoka, Takuya Higuchi, Mikihiro Tanaka, Li Li
2018	Misc	`conf`	Optimization of Speaker-Aware Multichannel Speech Extraction with ASR Criterion. ICASSP Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Takuya Higuchi, Tomohiro Nakatani, Jan Cernocký
2017	C	`conf`	Adversarial training for data-driven speech enhancement without parallel corpus. ASRU Takuya Higuchi, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani
2017	A	`conf`	Deep Clustering-Based Beamforming for Separation with Unknown Number of Sources. INTERSPEECH Takuya Higuchi, Keisuke Kinoshita, Marc Delcroix, Katerina Zmolíková, Tomohiro Nakatani
2017	Misc	`conf`	Deep mixture density network for statistical model-based feature enhancement. ICASSP Keisuke Kinoshita, Marc Delcroix, Atsunori Ogawa, Takuya Higuchi, Tomohiro Nakatani
2017	Misc	`conf`	Integrating DNN-based and spatial clustering-based mask estimation for robust MVDR beamforming. ICASSP Tomohiro Nakatani, Nobutaka Ito, Takuya Higuchi, Shoko Araki, Keisuke Kinoshita
2017	C	`conf`	Learning speaker representation for neural network based multichannel speaker extraction. ASRU Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Takuya Higuchi, Atsunori Ogawa, Tomohiro Nakatani
2017	—	`ch.`	Multichannel Speech Enhancement Approaches to DNN-Based Far-Field Speech Recognition. New Era for Robust Speech Recognition, Exploiting Deep Learning Marc Delcroix, Takuya Yoshioka, Nobutaka Ito, Atsunori Ogawa, Keisuke Kinoshita, Masakiyo Fujimoto, Takuya Higuchi, Shoko Araki, Tomohiro Nakatani
2017	J	`jnl`	Online MVDR Beamformer Based on Complex Gaussian Mixture Model With Spatial Prior for Noise Robust ASR. IEEE ACM Trans. Audio Speech Lang. Process. Takuya Higuchi, Nobutaka Ito, Shoko Araki, Takuya Yoshioka, Marc Delcroix, Tomohiro Nakatani
2017	—	`conf`	Online meeting recognition in noisy environments with time-frequency mask based MVDR beamforming. HSCMA Shoko Araki, Nobutaka Ito, Marc Delcroix, Atsunori Ogawa, Keisuke Kinoshita, Takuya Higuchi, Takuya Yoshioka, Dung T. Tran, Shigeki Karita, Tomohiro Nakatani
2017	A	`conf`	Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures. INTERSPEECH Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Takuya Higuchi, Atsunori Ogawa, Tomohiro Nakatani
2017	Misc	`conf`	Unsupervised utterance-wise beamformer estimation with speech recognition-level criterion. ICASSP Takuya Higuchi, Takuya Yoshioka, Keisuke Kinoshita, Tomohiro Nakatani
2016	A	`conf`	Optimization of Speech Enhancement Front-End with Speech Recognition-Level Criterion. INTERSPEECH Takuya Higuchi, Takuya Yoshioka, Tomohiro Nakatani
2016	Misc	`conf`	Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise. ICASSP Takuya Higuchi, Nobutaka Ito, Takuya Yoshioka, Tomohiro Nakatani
2016	A	`conf`	Semi-Supervised Joint Enhancement of Spectral and Cepstral Sequences of Noisy Speech. INTERSPEECH Li Li, Hirokazu Kameoka, Takuya Higuchi, Hiroshi Saruwatari
2016	—	`conf`	Sparseness-based multichannel nonnegative matrix factorization for blind source separation. IWAENC Takuya Higuchi, Takuya Yoshioka, Tomohiro Nakatani
2016	Misc	`conf`	Spatial correlation model based observation vector clustering and MVDR beamforming for meeting recognition. ICASSP Shoko Araki, Masahiro Okada, Takuya Higuchi, Atsunori Ogawa, Tomohiro Nakatani
2015	C	`conf`	The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices. ASRU Takuya Yoshioka, Nobutaka Ito, Marc Delcroix, Atsunori Ogawa, Keisuke Kinoshita, Masakiyo Fujimoto, Chengzhu Yu, Wojciech J. Fabian, Miquel Espi, Takuya Higuchi, Shoko Araki, Tomohiro Nakatani
2015	—	`conf`	Unified approach for audio source separation with multichannel factorial HMM and DOA mixture model. EUSIPCO Takuya Higuchi, Hirokazu Kameoka
2014	A	`conf`	A unified approach for underdetermined blind signal separation and source activity detection by multichannel factorial hidden Markov models. INTERSPEECH Takuya Higuchi, Hirofumi Takeda, Tomohiko Nakamura, Hirokazu Kameoka
2014	—	`conf`	Joint audio source separation and dereverberation based on multichannel factorial hidden Markov model. MLSP Takuya Higuchi, Hirokazu Kameoka
2014	Misc	`conf`	Underdetermined blind separation and tracking of moving sources based ONDOA-HMM. ICASSP Takuya Higuchi, Norihiro Takamune, Tomohiko Nakamura, Hirokazu Kameoka
2014	—	`conf`	Unified approach for underdetermined BSS, VAD, dereverberation and DOA estimation with multichannel factorial HMM. GlobalSIP Takuya Higuchi, Hirokazu Kameoka
2001	A*	`conf`	Remote Ultrasound Diagnostic System. ICRA Mamoru Mitsuishi, Shin'ichi Warisawa, Taishi Tsuda, Takuya Higuchi, Norihiro Koizumi, Hiroyuki Hashizume, Kazuo Fujiwara