Kazuhito Koishida

73 papers A* 7A 11B 1C 2Misc 15Journal 30Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	CUA-Skill: Develop Skills for Computer Using Agent. CoRR Tianyi Chen, Yinheng Li, Michael Solodko, Sen Wang, Nan Jiang, Tingyuan Cui, Junheng Hao, Jongwoo Ko, Sara Abdali, Suzhen Zheng, Leon Xu, Hao Fan, Pashmina Cameron, Justin Wagle, Kazuhito Koishida
2026	—	`conf`	Do GUI Grounders Truly Understand UI Elements? EACL (Findings) Surgan Jandial, Yinheng Li, Justin Wagle, Kazuhito Koishida
2025	J	`jnl`	AppSelectBench: Application-Level Tool Selection Benchmark. CoRR Tianyi Chen, Michael Solodko, Sen Wang, Jongwoo Ko, Junheng Hao, Colby R. Banbury, Sara Abdali, Saeed Amizadeh, Qing Xiao, Yinheng Li, Tianyu Ding, Kamran Ghasedi Dizaji, Suzhen Zheng, Hao Fan, Justin Wagle, Pashmina Cameron, Kazuhito Koishida
2025	A*	`conf`	Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression. CVPR Xiaoyi Qu, David Aponte, Colby R. Banbury, Daniel P. Robinson, Tianyu Ding, Kazuhito Koishida, Ilya Zharkov, Tianyi Chen
2025	J	`jnl`	Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression. CoRR Xiaoyi Qu, David Aponte, Colby R. Banbury, Daniel P. Robinson, Tianyu Ding, Kazuhito Koishida, Ilya Zharkov, Tianyi Chen
2025	Misc	`conf`	CorrGAN: Simultaneous Learning of Speech Enhancement and Perceptual Quality Loss Functions. ICASSP Vasily Zadorozhnyy, Saeed Amizadeh, Qiang Ye, Kazuhito Koishida
2025	J	`jnl`	Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems. CoRR Saeed Amizadeh, Sara Abdali, Yinheng Li, Kazuhito Koishida
2025	J	`jnl`	Instruction Agent: Enhancing Agent with Expert Demonstration. CoRR Yinheng Li, Hailey Hultquist, Justin Wagle, Kazuhito Koishida
2025	J	`jnl`	Self-reflecting Large Language Models: A Hegelian Dialectical Approach. CoRR Sara Abdali, Can Goksen, Saeed Amizadeh, Kazuhito Koishida
2025	A*	`conf`	VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks. ICLR Lawrence Keunho Jang, Yinheng Li, Dan Zhao, Charles Ding, Justin Lin, Paul Pu Liang, Rogerio Bonatti, Kazuhito Koishida
2025	J	`jnl`	WinClick: GUI Grounding with Multimodal Large Language Models. CoRR Zheng Hui, Yinheng Li, Dan Zhao, Tianyi Chen, Colby R. Banbury, Kazuhito Koishida
2025	—	`conf`	WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models. ACL (2) Zheng Hui, Yinheng Li, Dan Zhao, Colby R. Banbury, Tianyi Chen, Kazuhito Koishida
2025	A*	`conf`	Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale. ICML Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Keunho Jang, Zheng Hui
2024	J	`jnl`	Automatic Disfluency Detection From Untranscribed Speech. IEEE ACM Trans. Audio Speech Lang. Process. Amrit Romana, Kazuhito Koishida, Emily Mower Provost
2024	A	`conf`	ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation. INTERSPEECH Yatong Bai, Trung Dang, Dung N. Tran, Kazuhito Koishida, Somayeh Sojoudi
2024	J	`jnl`	Data Generation Using Large Language Models for Text Classification: An Empirical Case Study. CoRR Yinheng Li, Rogerio Bonatti, Sara Abdali, Justin Wagle, Kazuhito Koishida
2024	B	`conf`	Learned Image Compression With Text Quality Enhancement. ICIP Chih-Yu Lai, Dung N. Tran, Kazuhito Koishida
2024	J	`jnl`	Learned Image Compression with Text Quality Enhancement. CoRR Chih-Yu Lai, Dung N. Tran, Kazuhito Koishida
2024	A	`conf`	LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes. INTERSPEECH Trung Dang, David Aponte, Dung N. Tran, Kazuhito Koishida
2024	J	`jnl`	LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes. CoRR Trung Dang, David Aponte, Dung N. Tran, Kazuhito Koishida
2024	J	`jnl`	VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks. CoRR Lawrence Jang, Yinheng Li, Charles Ding, Justin Lin, Paul Pu Liang, Dan Zhao, Rogerio Bonatti, Kazuhito Koishida
2024	A*	`conf`	Weakly-supervised Audio Separation via Bi-modal Semantic Similarity. ICLR Tanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu
2024	J	`jnl`	Weakly-supervised Audio Separation via Bi-modal Semantic Similarity. CoRR Tanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu
2024	J	`jnl`	Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale. CoRR Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Jang, Zack Hui
2024	J	`jnl`	Zero-Shot Text-to-Speech from Continuous Text Streams. CoRR Trung Dang, David Aponte, Dung N. Tran, Tianyi Chen, Kazuhito Koishida
2024	Misc	`conf`	uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures. ICASSP Afrina Tabassum, Dung N. Tran, Trung Dang, Ismini Lourentzou, Kazuhito Koishida
2024	J	`jnl`	uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures. CoRR Afrina Tabassum, Dung N. Tran, Trung Dang, Ismini Lourentzou, Kazuhito Koishida
2023	J	`jnl`	Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation. CoRR Yatong Bai, Trung Dang, Dung N. Tran, Kazuhito Koishida, Somayeh Sojoudi
2023	J	`jnl`	Automatic Disfluency Detection from Untranscribed Speech. CoRR Amrit Romana, Kazuhito Koishida, Emily Mower Provost
2023	—	`conf`	Improving Low-Latency Mono-Channel Speech Enhancement by Compensation Windows in STFT Analysis. COMPLEX NETWORKS (1) Minh N. Bui, Dung N. Tran, Kazuhito Koishida, Trac D. Tran, Peter Chin
2023	A*	`conf`	Progressive Ensemble Distillation: Building Ensembles for Efficient Inference. NeurIPS Don Kurian Dennis, Abhishek Shetty, Anish Prasad Sevekari, Kazuhito Koishida, Virginia Smith
2023	J	`jnl`	Progressive Knowledge Distillation: Building Ensembles for Efficient Inference. CoRR Don Kurian Dennis, Abhishek Shetty, Anish Sevekari, Kazuhito Koishida, Virginia Smith
2023	A	`conf`	SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks. INTERSPEECH Vasily Zadorozhnyy, Qiang Ye, Kazuhito Koishida
2023	J	`jnl`	Single-channel speech enhancement using learnable loss mixup. CoRR Oscar Chang, Dung N. Tran, Kazuhito Koishida
2023	Misc	`conf`	Toward A Multimodal Approach for Disfluency Detection and Categorization. ICASSP Amrit Romana, Kazuhito Koishida
2022	Misc	`conf`	A Training Framework for Stereo-Aware Speech Enhancement Using Deep Neural Networks. ICASSP Bahareh Tolooshams, Kazuhito Koishida
2022	J	`jnl`	SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks. CoRR Vasily Zadorozhnyy, Qiang Ye, Kazuhito Koishida
2022	Misc	`conf`	Training Robust Zero-Shot Voice Conversion Models with Self-Supervised Features. ICASSP Trung Dang, Dung N. Tran, Peter Chin, Kazuhito Koishida
2021	J	`jnl`	A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networks. CoRR Bahareh Tolooshams, Kazuhito Koishida
2021	J	`jnl`	Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations. CoRR Melikasadat Emami, Dung N. Tran, Kazuhito Koishida
2021	Misc	`conf`	Cascaded Time + Time-Frequency Unet For Speech Enhancement: Jointly Addressing Clipping, Codec Distortions, And Gaps. ICASSP Arun Asokan Nair, Kazuhito Koishida
2021	A	`conf`	INTERSPEECH 2021 Deep Noise Suppression Challenge. Interspeech Chandan K. A. Reddy, Harishchandra Dubey, Kazuhito Koishida, Arun Asokan Nair, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper, Robert Aichner, Sriram Srinivasan
2021	J	`jnl`	Interspeech 2021 Deep Noise Suppression Challenge. CoRR Chandan K. A. Reddy, Harishchandra Dubey, Kazuhito Koishida, Arun Asokan Nair, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper, Robert Aichner, Sriram Srinivasan
2021	A	`conf`	Single-Channel Speech Enhancement Using Learnable Loss Mixup. Interspeech Oscar Chang, Dung N. Tran, Kazuhito Koishida
2021	J	`jnl`	Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features. CoRR Trung Dang, Dung N. Tran, Peter Chin, Kazuhito Koishida
2020	Misc	`conf`	AV(SE) ICASSP Michael L. Iuzzolino, Kazuhito Koishida
2020	Misc	`conf`	Geometrically Constrained Independent Vector Analysis for Directional Speech Enhancement. ICASSP Li Li, Kazuhito Koishida
2020	—	`conf`	Improved Active Speaker Detection based on Optical Flow. CVPR Workshops Chong Huang, Kazuhito Koishida
2020	A	`conf`	Low-Latency Single Channel Speech Dereverberation Using U-Net Convolutional Neural Networks. INTERSPEECH Ahmet Emin Bulut, Kazuhito Koishida
2020	Misc	`conf`	Low-Latency Single Channel Speech Enhancement Using U-Net Convolutional Neural Networks. ICASSP Ahmet Emin Bulut, Kazuhito Koishida
2020	A*	`conf`	MMTM: Multimodal Transfer Module for CNN Fusion. CVPR Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L. Iuzzolino, Kazuhito Koishida
2020	A*	`conf`	Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning". ICML Saeed Amizadeh, Hamid Palangi, Alex Polozov, Yichen Huang, Kazuhito Koishida
2020	J	`jnl`	Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning". CoRR Saeed Amizadeh, Hamid Palangi, Oleksandr Polozov, Yichen Huang, Kazuhito Koishida
2020	A	`conf`	Online Directional Speech Enhancement Using Geometrically Constrained Independent Vector Analysis. INTERSPEECH Li Li, Kazuhito Koishida, Shoji Makino
2020	A	`conf`	Robust Pitch Regression with Voiced/Unvoiced Classification in Nonstationary Noise Environments. INTERSPEECH Dung N. Tran, Uros Batricevic, Kazuhito Koishida
2020	A	`conf`	Single-Channel Speech Enhancement by Subspace Affinity Minimization. INTERSPEECH Dung N. Tran, Kazuhito Koishida
2019	J	`jnl`	Adversarial Training for Speech Super-Resolution. IEEE J. Sel. Top. Signal Process. Sefik Emre Eskimez, Kazuhito Koishida, Zhiyao Duan
2019	J	`jnl`	MMTM: Multimodal Transfer Module for CNN Fusion. CoRR Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L. Iuzzolino, Kazuhito Koishida
2019	A	`conf`	Sound Event Detection in Multichannel Audio Using Convolutional Time-Frequency-Channel Squeeze and Excitation. INTERSPEECH Wei Xia, Kazuhito Koishida
2019	J	`jnl`	Sound Event Detection in Multichannel Audio using Convolutional Time-Frequency-Channel Squeeze and Excitation. CoRR Wei Xia, Kazuhito Koishida
2019	Misc	`conf`	Speech Super Resolution Generative Adversarial Network. ICASSP Sefik Emre Eskimez, Kazuhito Koishida
2018	J	`jnl`	Text-Independent Speaker Verification Based on Triplet Convolutional Neural Network Embeddings. IEEE ACM Trans. Audio Speech Lang. Process. Chunlei Zhang, Kazuhito Koishida, John H. L. Hansen
2017	A	`conf`	End-to-End Text-Independent Speaker Verification with Triplet Loss on Short Utterances. INTERSPEECH Chunlei Zhang, Kazuhito Koishida
2017	C	`conf`	End-to-end text-independent speaker verification with flexibility in utterance duration. ASRU Chunlei Zhang, Kazuhito Koishida
2008	C	`conf`	Hybrid low bitrate audio coding using adaptive gain shape vector quantization. MMSP Sanjeev Mehrotra, Wei-Ge Chen, Kazuhito Koishida, Naveen Thumpudi
2000	Misc	`conf`	A 1200 bps speech coder based on MELP. ICASSP Tian Wang, Kazuhito Koishida, Vladimir Cuperman, Allen Gersho, John S. Collura
2000	Misc	`conf`	A 16-kbit/s bandwidth scalable audio coder based on the G.729 standard. ICASSP Kazuhito Koishida, Vladimir Cuperman, Allen Gersho
1998	—	`conf`	A 16 kbit/s wideband CELP coder using MEL-generalized cepstral analysis and its subjective evaluation. ICSLP Kazuhito Koishida, Gou Hirabayashi, Keiichi Tokuda, Takao Kobayashi
1998	Misc	`conf`	A wideband CELP speech coder at 16 kbit/s based on mel-generalized cepstral analysis. ICASSP Kazuhito Koishida, Gou Hirabayashi, Keiichi Tokuda, Takao Kobayashi
1997	Misc	`conf`	Efficient encoding of mel-generalized cepstrum for CELP coders. ICASSP Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai
1996	—	`conf`	CELP coding system based on mel-generalized cepstral analysis. ICSLP Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai
1995	Misc	`conf`	CELP coding based on mel-cepstral analysis. ICASSP Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai
1994	—	`conf`	Speech coding based on adaptive MEL-cepstral analysis for noisy channels. ICSLP Kazuhito Koishida, Keiichi Tokuda, Takao Kobayashi, Satoshi Imai