IEICE Technical Report

Online edition: ISSN 2432-6380

Volume 125, Number 371

Speech

[PREV] [NEXT]

[TOP] | [2020] | [2021] | [2022] | [2023] | [2024] | [2025] | [2026] | [Japanese] / [English]

[PROGRAM] [BULK PDF DOWNLOAD]

Table of contents

SP2025-26
A Study on Japanese Text Strings for LLM-based Text-to-Speech
Kiyoshi Kurihara (UTokyo)
pp. 1 - 6

SP2025-27
A Preliminary Study on Japanese Accent Conversion Using Prosody Suppression Effect of HuBERT Tokens
Tomoaki Mizuno (UEC/AIST), Hitoshi Suda, Tomohiko Nakamura, Satoru Fukayama (AIST), Toru Nakashika (UEC)
pp. 7 - 12

SP2025-28
Text-to-Action-to-Speech Using Vocal Tract Parameter Representation and Reinforcement Learning
Akiko Ono (Keio Univ.), Norihiro Kato (Hokkaido Univ.), Shinnosuke Takamichi (Keio Univ.)
pp. 13 - 18

SP2025-29
Comparative Evaluation of TTS and Speech Synthesis Models for Visual Speech-Based Speech Generation
Shin Wakizaka, Haibo Zhang, Takeshi Saitoh (Kyutech)
pp. 19 - 24

SP2025-30
Relationship between Interoception and Neural Activity Networks during Music Recall
Naoki Otsuka, Kazuki Matsunaga, Mayu Goto, Ingon Chanpornpakdi, Toshihisa Tanaka (TUAT)
pp. 25 - 30

SP2025-31
Neural Correlates of Music-Induced Awe: An Investigation of EEG Power and Functional Connectivity
Mayu Goto (TUAT), Motoko Iwashita (DENSO CORP.), Ingon Chanpornpakdi (TUAT), Makiko Ishikawa, Kenji Ishida (DENSO CORP.), Toshihisa Tanaka (TUAT)
pp. 31 - 36

SP2025-32
Advanced Real-Time Anomaly Detection in Power Grid Networks State Estimation Using Graph Signal Processing Techniques.
SadaTukur, Shogo Muramatsu (Niigata Univ.)
pp. 37 - 42

SP2025-33
Supervised Machine Learning Techniques for Fault Detection and Classification in Photovoltaic (PV) Systems
Ahmed Malouq, Shogo Muramatsu (Niigata Univ.)
pp. 43 - 48

SP2025-34
Underdetermined Unsupervised Signal Segregation by Switching Beamforming with Time-Frequency Masks
Atsuhisa Nakane, Kouei Yamaoka, Norihiro Takamune, Hiroshi Saruwatari (UTokyo), Daichi Kitamura (National Institute of Technology, Kagawa College), Rintaro Ikeshita, Tomohiro Nakatani (NTT)
pp. 49 - 56

SP2025-35
Iterative Source Steering under Subspace Constraints for Multichannel Source Separation
Yutsuki Takeuchi, Taishi Nakashima, Nobutaka Ono (Tokyo Metropolitan Univ.)
pp. 57 - 62

SP2025-36
Joint Optimization of Demixing Filters and Sampling Rate Offsets via Auxiliary-Function Approach
Hayato Takeuchi, Takao Kawamura, Nobutaka Ono (Tokyo Metropolitan Univ.), Shoko Araki (NTT)
pp. 63 - 68

SP2025-37
[Poster Presentation] Sound Source Localization Based on the Reliability of Estimated Inter - Channel Group Delay
Shun Hatano, Kenji Suyama (Tokyo Denki Univ.)
pp. 69 - 74

SP2025-38
[Poster Presentation] Two-Microphone Signal Extraction Using Multiple Directional Pattern-Forming Circuits
Miryu Goino, Kenji Suyama (Tokyo Denki Univ.)
pp. 75 - 80

SP2025-39
[Poster Presentation] Two-Microphone Sound Source Localization Focused on Extracting Single-Source Bins
Riku Kamoto, Kenji Suyama (Tokyo Denki Univ.)
pp. 81 - 86

SP2025-40
[Poster Presentation] A study on a k-medoids-based sampling strategy for efficient training of auditory perception models -- An evaluation on reverberation time prediction --
Takumi Koga, Natsuki Ueno (Kumamoto Univ.), Kenji Ishizuka, Akito Nakamura, Yu Takahashi (Yamaha Corp.)
pp. 87 - 92

SP2025-41
[Poster Presentation] Inner diameter tuning based on CT image brightness of Shakuhachi and evaluation of reproduction by additive manufacturing
Mizuki Nakao, Soichiro Sudo, Akisato Mizuno, Yoshinori Takahashi (Kogakuin Univ.)
pp. 93 - 98

SP2025-42
[Poster Presentation] Effects of Vibration Devices on Subjective Impressions in Music Listening
Takayuki Ohara, Mituhiro Nakagawara (NIT,KC), Mitunori Mizumati (KIT)
pp. 99 - 102

SP2025-43
[Poster Presentation] Synchronized Analysis of Acoustic Radiation Dynamics in Balloon Bursts via High-Speed Imaging and High-Temporal-Resolution Acoustic Measurements
Hayato Muroga, Tsubasa Kusano, Kan Okubo (Tokyo Metoropolitan Univ.)
pp. 103 - 107

SP2025-44
(See Japanese page.)
pp. 108 - 113

SP2025-45
[Poster Presentation] Text-Based Instrument Conditioning for Instrument-Wise Music Similarity Representation Learning
Takehiro Imamura, Yuka Hashizume, Wen-Chin Huang, Tomoki Toda (Nagoya Univ.)
pp. 114 - 120

SP2025-46
[Poster Presentation] A Data Augmentation Method for Music Source Separation Using MLP-based Training Data Selection
Yuma Hirahara, Akitoshi Kataoka (Ryukoku Univ.)
pp. 121 - 126

SP2025-47
[Poster Presentation] Blind source separation using distributed microphone arrays via distributed fast multichannel nonnegative matrix factorization
Hirotaka Nishikori (UTokyo), Nobutaka Ito (AIST), Kouei Yamaoka, Norihiro Takamune, Hiroshi Saruwatari (UTokyo)
pp. 127 - 132

SP2025-48
[Poster Presentation] Comparative Analysis of Auditory Response Characteristics to Repeated Pulse Stimulation -- Toward Experimental Verification of Bone Conduction Presentation and Microwave Auditory Effects --
Salam Hadi, Kan Okubo, Tsubasa Kusano (TMU), Yasuo Terao (KU), Masao Taki, Yukihisa Suzuki, Shoma Kishioka (TMU), Mayumi Okamoto, Kaoru Yuasa (KU)
pp. 133 - 137

SP2025-49
Monaural speech enhancement utilizing parallel and non-parallel data via deep learning based on surrogate set classification
Ryo Ogawa (UTokyo), Nobutaka Ito (AIST), Norihiro Takamune, Kouei Yamaoka, Hiroshi Saruwatari (UTokyo)
pp. 138 - 144

SP2025-50
Multi-channel Language-Queried Audio Source Separation for Moving Sources
Yuki Nakamura, Taishi Nakashima, Nobutaka Ono (Tokyo Metropolitan Univ.)
pp. 145 - 150

SP2025-51
A Semi-Automated Method for Constructing Environmental Sound Evaluation Datasets While Avoiding Unintended Overlap with Existing Datasets
Minoru Kishi (Keio Univ.), Shinnosuke Takamichi (Keio Univ./UTokyo), Riki Takizawa (KSU), Yusuke Kanamori (UTokyo), Noriyuki Tonami (NEC), Ryotaro Nagase (Rits), Keisuke Imoto (KyotoU), Yuki Okamoto (UTokyo)
pp. 151 - 158

SP2025-52
[Poster Presentation] Emoji Annotation of Speech Corpus and Its Application to Emotional Speech Synthesis
Ryota Kawamatsu, Takaki Hamada, Kazuki Yamauchi (UT), Yuki Saito (UT/AIST), Hiroshi Saruwatari (UT)
pp. 159 - 164

SP2025-53
[Poster Presentation] Self Voice Conversion as an Attack against Neural Audio Watermarking
Yigitcan Oezer, Wanying Ge, Zhe Zhang, Xin Wang, Junichi Yamagishi (NII)
pp. 165 - 170

SP2025-54
Effects of Routing Speech Likability Estimation through Voice-Quality Description Generation Using a Speech-Language Foundation Model
Norihiro Kato (Hokkaido Univ), Akiko Ono, Shinnosuke Takamichi (Keio Univ), Yoshinori Dobashi (Hokkaido Univ)
pp. 171 - 176

SP2025-55
[Poster Presentation] Perception of Sound Quality Degradation in Noisy Environments and Power-Saving Audio Playback
Yura Sakoda, Soichiro Togawa, Mitsuhiro Nkagawara (NIT,KC), Mitsunori Mizumachi (KIT)
pp. 177 - 180

SP2025-56
[Poster Presentation] Sound source localization using single microphone room impulse response and machine learning
Yuto Maezawa, Takao Tsuchiya (Doshisha)
pp. 181 - 186

SP2025-57
[Poster Presentation] A Proposal of an Audio-Language Model for Moving Sound Sources
Yuki Hayasaki, Kentaro Seki, Yuki Okamoto, Kouei Yamaoka, Yuki Saito, Hiroshi Saruwatari (UTokyo)
pp. 187 - 194

SP2025-58
(See Japanese page.)
pp. 195 - 200

SP2025-59
[Poster Presentation] A study on generating a fine HRIR set from a coarse HRIR set
Tsubasa Oshida, Masayuki Nishiguchi, Kanji Watanabe, Koji Abe (Akita Prefectural Univ.)
pp. 201 - 206

SP2025-60
[Poster Presentation] Investigation of a Single-Channel Audio Source Emphasis Model Using GNN
Taisuke Morikawa, Akitoshi Kataoka (Ryukoku Univ)
pp. 207 - 212

SP2025-61
[Poster Presentation] A Detection Method of Tampered Images Using Adversarial Perturbations in The Encrypted Domain
Olimov Mukhammadolim, Kouki Horio, Sayaka Shiota, Hitoshi Kiya (TMU)
pp. 213 - 217

SP2025-62
[Poster Presentation] Validation of the Effectiveness of Tight Windows for STFT Phase Retrieval
Atsuhiko Oshida, Keito Takahashi, Daichi Kitahara (Keio Univ.)
pp. 218 - 223

SP2025-63
[Poster Presentation] Spline Knot Placement Under Noise Using a Cumulative Distribution Function
Rumoi Tanabe, Hiroki Arai, Daichi Kitahara (Keio Univ.)
pp. 224 - 229

SP2025-64
[Poster Presentation] Validation of a Low-Latency Gauge Correction Algorithm for GSMaP in Japan
Jun Koizumi (Keio Univ.), Hitoshi Hirose, Tomoo Ushio (Osaka Univ.), Daichi Kitahara (Keio Univ.)
pp. 230 - 235

SP2025-65
[Poster Presentation] Rainfall Map Creation from Weather Radar Network via Convex Optimization
Oshiro Watanabe, Akira Egashira, Shinji Naito, Daichi Kitahara (Keio Univ.)
pp. 236 - 242

SP2025-66
(See Japanese page.)
pp. 243 - 246

SP2025-67
Proposal of a Sensory Evaluation Data Analysis Method for Expressing Value in Tactile Sensation
Miho Tanaka, Kiyotaka Komoku, Tomoyuki Yokogawa, Kazutami Arimoto (Okayama Prefectural Univ.), Hidekuni Takao (Kagawa Univ.)
pp. 247 - 252

SP2025-68
PHISWIDv2: Towards More Realistic Physics-inspired Synthesized Underwater Image Dataset
Reina Kaneko, Junya Hara, Hiroshi Higashi, Yuichi Tanaka (UOsaka)
pp. 253 - 258

SP2025-69
EEG-based Auditory Attention Decoding in Diotic Listening Environments
Masahiro Yoshino, Haruki Yokota, Junya Hara, Yuichi Tanaka, Hiroshi Higashi (UOsaka)
pp. 259 - 265

SP2025-70
Temporal Decodability Dynamics and Contribution Analysis for ECoG Spoken-Word Decoding
Tatsuya Takei, Shuji Komeiji, Shoya Murakami, Yu Watanabe (TUAT), Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano (JU), Koichi Shinoda (IST), Toshihisa Tanaka (TUAT)
pp. 266 - 271

SP2025-71
[Poster Presentation] Lyrics Intelligibility Prediction Based on Multiple Whisper Recognition Candidates Toward Improved Music Experience for Hearing-Impaired Listeners
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko (NTT)
pp. 272 - 276

SP2025-72
[Poster Presentation] Spoofing attacks using deepfake speech synthesized from non-consensual recordings
Sawato Furubayashi (Tokyo Metropotitan Univ.), Shinnosuke Takamichi (Keio Univ.), Sayaka Shiota (Tokyo Metropotitan Univ.)
pp. 277 - 282

SP2025-73
[Poster Presentation] J-SPAW2: A Japanese Speech Corpus for Analyzing Recording Conditions in Replay Attacks
Suzuka Horie (Tokyo Metropolitan Univ.), Shinnosuke Takamichi (Keio Univ.), Sayaka Shiota (Tokyo Metropolitan Univ.)
pp. 283 - 288

SP2025-74
[Poster Presentation] Analysis of Pre-trained Models Based on Information Retention of Key Acoustic Functionals for Subjective Singing MOS Evaluation
Ryoko Arita, Yuki Saito (UT/AIST), Hiroshi Saruwatari (UT)
pp. 289 - 294

SP2025-75
[Poster Presentation] Unseen Speaker Voice Conversion Using Speaker-Aware Contrastive Learning
Taigo Kaneko, Toru Nakashika (UEC)
pp. 295 - 300

SP2025-76
[Poster Presentation] Voice Conversion with Contrastive Pretrained Audio Encoder
Haruto Sato, Toru Nakashika (UEC)
pp. 301 - 305

SP2025-77
[Poster Presentation] Performance Evaluation of VAE-SiFiGAN under Large-Scale Training and Noisy Conditions
Kenichi Ogita, Reo Yoneyama, Wen-Chin Huang, Tomoki Toda (Nagoya Univ.)
pp. 306 - 311

SP2025-78
[Poster Presentation] Fast Adversarial Speech Generation for Speaker Recognition Using a Pretrained Noise Generator
Kotaro Nakamura, Toru Nakashika (UEC)
pp. 312 - 317

SP2025-79
[Poster Presentation] Context Dependency in Automatic Speech Recognition: Analyzing Mamba's Effectiveness
Joichiro Sato, Yosuke Higuchi, Tetsunori Kobayashi, Tetsuji Ogawa (Waseda Univ.)
pp. 318 - 323

SP2025-80
[Poster Presentation] Multi-talker Speech Recognition Using Intermediate Representation Correction for Overlapped Speech Segments Based on Local and Global Attention
Keigo Kojima, Higuti Yousuke, Kobayasi Tetsunori, Ogawa Tetsuji (Waseda Univ)
pp. 324 - 329

SP2025-81
[Invited Talk] Acoustic distance measurement method to target based on phase interference of audible sound -- From the principle to the current progress --
Noboru Nakasako, Tetsuji Uebo, Toshihiro Shinohara (Kindai UNiv.), Masato Nakayama (Ritsumeikan UNiv.)
p. 330

SP2025-82
Cross-Modal Representation Learning for Sound Retrieval from Onomatopoeia Images
Yamato Kojima (Doshisha Univ.), Keisuke Imoto (Kyoto Univ.), Takao Tsuchiya (Doshisha Univ.)
pp. 331 - 334

SP2025-83
(See Japanese page.)
pp. 335 - 337

SP2025-84
Learning Disentangled Source and Spatial Representations From Spatial Audio-Text Contrastive Learning
Shotaro Ueji, Shinnosuke Takamichi (Keio Univ.), Kouei Yamaoka (UTokyo)
pp. 338 - 343

SP2025-85
Application and performance evaluation of MERT features in award-based comparison of All Japan Band Competition recordings
Kai Hiraiwa, Satoru Fukayama (AIST)
pp. 344 - 349

SP2025-86
[Poster Presentation] Analysing the Noise Robustness of Neural Audio Codecs -- Relationship between Language Statistical Structure and Degraded Speech Based on Zipf's Law and Heaps' Law --
Joonyong Park (UTokyo), Shinnosuke Takamichi (KeioU), David M. Chan (UCB), Shunsuke Kando, Yuki Saito, Hiroshi Saruwatari (UTokyo)
pp. 350 - 355

SP2025-87
(See Japanese page.)
pp. 356 - 361

SP2025-88
(See Japanese page.)
pp. 362 - 367

SP2025-89
[Poster Presentation] Analysis of Impacts of Input Audio Characteristics on Adversarial Attacks Against Speaker Verification
Daiki Kawahara, Ren Miyamoto, Daisuke Saito, Nobuaki Minematsu (UTokyo)
pp. 368 - 373

SP2025-90
[Poster Presentation] Evaluation of Lipschitz constants for time-frequency masking-based DNNs with Guaranteed Lipschitz continuity
Kazuki Matsumoto, Ren Uchida, Kohei Yatabe (TUAT)
pp. 374 - 379

SP2025-91
[Poster Presentation] Speech Intelligibility Improvement using S2T2S
Nagare Ouchi, Yousuke Sugiura, Tetsuya Shimamura (Saitama Univ.)
pp. 380 - 384

SP2025-92
[Poster Presentation] Joint Optimization of Source Separation and Turn-Taking Prediction in Spoken Dialogue
Yusaku Mizobuchi, Koji Inoue, Keisuke Imoto, Kazuyoshi Yoshii, Tatsuya Kawahara (Kyoto Univ.)
pp. 385 - 390

SP2025-93
[Poster Presentation] NeuWORLD: A Neural Signal Processing Vocoder Based on Periodic, Aperiodic, and Filter
Yuto Ashida, Toru Nakashika (UEC)
pp. 391 - 395

SP2025-94
Robust Koopman Operator Estimation Against Impulsive Noise Using Adaptive Projected Subgradient Method
Haru Honda, Masahiro Yukawa (Keio Univ.)
pp. 396 - 400

SP2025-95
Solving differential equations in time-frequency domain
Shigeru Ando (Univ. Tokyo)
pp. 401 - 406

SP2025-96
A Design of Monotone Lipschitz Gradient Denoiser Using Diffusion Model: Towards Explainable Plug-and-Play Method for Image Restoration
Riki Suzuki, Masahiro Yukawa (Keio)
pp. 407 - 412

SP2025-97
Automated Hyperparameter Optimization for Compressed Sensing Algorithm Based on Hypergradient Descent
Yusuke Nakane, Ayano Nakai-Kasai, Tadashi Wadayama (NIT)
pp. 413 - 418

SP2025-98
[Poster Presentation] A Study of Acoustic Jamming against Eavesdropping via the Malicious Use of Blind Source Separation
Taishi Nakashima (TMU)
pp. 419 - 424

SP2025-99
(See Japanese page.)
pp. 425 - 430

SP2025-100
[Poster Presentation] Partially Centralized Algorithm for Independent Low-Rank Matrix Analysis on Ad-hoc Microphone Arrays
Yuta Haruyama, Kouei Yamaoka, Norihiro Takamune, Hiroshi Saruwatari (UTokyo)
pp. 431 - 438

SP2025-101
[Poster Presentation] Performance Improvement of Multi-Component Drum Separation via NMF with Time-Frequency Controlled Dictionary Learning
Yuri Maejima, Natsuki Yoshino, Akira Tanaka (Hokudai)
pp. 439 - 446

SP2025-102
[Poster Presentation] Study on a Multi-Channel ANC System Employing Online Secondary Path Modelling with Channel Decorrelation
Fuma Tsujiwaki, Shota Toyooka, Yoshinobu Kajikawa (Kansai Univ.)
pp. 447 - 454

SP2025-103
[Poster Presentation] A Study on Parameter Estimation of Equivalent Circuit for Balanced Armature Transducer
Yusuke Umemiya, Shota Toyooka (Kansai Univ), Shunsuke Kita (ORIST), Yoshinobu Kajikawa (Kansai Univ)
pp. 455 - 460

SP2025-104
[Poster Presentation] Design and Implementation of Battery-Operated Compact Acoustic Suction Tweezers for Mobile Applications
Shoya Yoneda, Yusei Yokoyama, Tsubasa Kusano, Kan Okubo (Tokyo Metropolitan Univ.)
pp. 461 - 464

SP2025-105
[Poster Presentation] A Study on Crosstalk Cancellation based on the DAIF Method in Portable Parametric Array Loudspeaker
Hinata Taninoguchi, Shota Toyooka (KU), Kenta Iwai (OSU), Yoshinobu Kajikawa (KU)
pp. 465 - 470

SP2025-106
[Poster Presentation] A study on the side-lobe suppression in parametric array loudspeaker using optimization technique
Ryu Nakagawa, Shota Toyooka (Kansai Univ.), Kenta Iwai (Osaka Sangyo Univ.), Yoshinobu Kajikawa (Kansai Univ.)
pp. 471 - 476

SP2025-107
[Poster Presentation] Vibro-Acoustic Coupling Analysis of the Relationship Between Diaphragm Geometry and Directivity in Shell-Structured Distributed Mode Loudspeakers
Yuito Kimura, Tsubasa Kusano, Kan Okubo (TMU)
pp. 477 - 482

SP2025-108
[Poster Presentation] Study on Multi Channel Dual Active Noise Control Systems Using Directional Microphones
Takuma Sendo, Shota Toyooka (Kansai Univ.), Kenta Iwai (Osaka Sangyo Univ.), Yoshinobu Kajikawa (Kansai Univ.)
pp. 483 - 488

SP2025-109
(See Japanese page.)
pp. 489 - 494

SP2025-110
[Invited Talk] Time-Series Understanding via Mapping to Natural-Language Concepts
Kota Dohi (Hitachi)
p. 495

SP2025-111
An Experimental Study on the Language Dependency of Text-independent Speaker Verification under Well-controlled Conditions
Riko Nakamura (YCU), Akira Gotoh, Yuko Saito, Hiroki Matsuura (NEC), Takafumi Koshinaka (YCU)
pp. 496 - 501

SP2025-112
[Poster Presentation] Water Level Distribution Prediction by Data Assimilation on Graphs for Integrated River Control
Maki Soma, Hiromu Kanauchi, Ryuto Ito, Hiroyasu Yasuda (Niigata Univ.), Masaaki Nagahara (Hiroshima Univ.), Shogo Muramatsu (Niigata Univ.)
pp. 502 - 507

SP2025-113
[Poster Presentation] Alignment of Similarity-Transformed Images via Cross-Correlation Maximization Based on Auxiliary Function Method
Shinji Yamashita, Yuma Kinoshita (Tokai Univ.), Hitoshi Kiya (TMU)
pp. 508 - 513

SP2025-114
[Poster Presentation] Signal Enhancement by Random Sampling for Steady State Visual Evoked Potential BCI
Yoshikazu Washizawa (UEC)
pp. 514 - 519

SP2025-115
[Poster Presentation] Construction of a Unique Graph Fourier Transform Independent of the Implementation of Spectral Decomposition
Takuya Miyazawa, Natsuki Yoshino, Akira Tanaka (Hokkaido Univ.)
pp. 520 - 525

SP2025-116
[Poster Presentation] ARivE: A Water Level Distribution Prediction Application for Integrated River Water Level Monitoring and Control
Ryuto Ito, Hiromu Kanauchi, Hiroyasu Yasuda (Niigata Univ.), Masaaki Nagahara (Hiroshima Univ.), Shogo Muramatsu (Niigata Univ.)
pp. 526 - 531

SP2025-117
[Poster Presentation] Domain-Adaptive Online Learning for EEG-Based Emotion Recognition under Subject-Independent Conditions
Kotaro Mori, Yoshikazu Washizawa (UEC)
pp. 532 - 537

SP2025-118
[Poster Presentation] Evaluation of Sustained Attention to Spoken Language Using EEG-Based Speech Envelope Tracking
Yoshinao Ichikawa, Yoshikazu Washizawa (UEC)
pp. 538 - 543

SP2025-119
[Poster Presentation] Improving the Precision of on Acoustic Imaging of Invisible Regions Using Highly Directional Source and Pulse Compression Technique
Raimu Komatsu, Tsubasa Kusano, Kan Okubo (Tokyo Metropolitan Univ.)
pp. 544 - 549

SP2025-120
[Poster Presentation] Douglas-Rachford Splitting for Feasibility-Based Quantized and Low-Rank Decomposition of Neural Network Weights
Haruto Suzuki, Masao Yamagishi (Hosei Univ.)
pp. 550 - 555

SP2025-121
[Poster Presentation] A Comparison-Efficient Method for Ternary Quantization of Neural Network Weights
Yuto Goto, Masao Yamagishi (Hosei Univ.)
pp. 556 - 561

SP2025-122
[Poster Presentation] Extension of phase retrieval algorithms for nanoimaging of submillimeter-thick samples
Natsuki Akaishi, Kohei Yatabe (TUAT), Yuki Takayama (Tohoku Univ.)
pp. 562 - 567

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.