Naoki Makishima

60 papers A* 3A 15B 2C 3Misc 4Journal 23Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models. AAAI Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Taiga Yamane, Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2025	J	`jnl`	Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models. CoRR Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Taiga Yamane, Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2025	C	`conf`	Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model. ASRU Mana Ihori, Taiga Yamane, Naotaka Kawata, Naoki Makishima, Tomohiro Tanaka, Satoshi Suzuki, Shota Orihashi, Ryo Masumura
2025	—	`conf`	Joint Modeling of Big Five and HEXACO for Multimodal Apparent Personality-Trait Recognition. APSIPA Ryo Masumura, Shota Orihashi, Mana Ihori, Tomohiro Tanaka, Naoki Makishima, Taiga Yamane, Naotaka Kawata, Satoshi Suzuki, Taichi Katayama
2025	J	`jnl`	Joint Modeling of Big Five and HEXACO for Multimodal Apparent Personality-trait Recognition. CoRR Ryo Masumura, Shota Orihashi, Mana Ihori, Tomohiro Tanaka, Naoki Makishima, Taiga Yamane, Naotaka Kawata, Satoshi Suzuki, Taichi Katayama
2025	J	`jnl`	MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection. CoRR Taiga Yamane, Satoshi Suzuki, Ryo Masumura, Shota Orihashi, Tomohiro Tanaka, Mana Ihori, Naoki Makishima, Naotaka Kawata
2025	A*	`conf`	Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level Scores. AAAI Ryo Masumura, Shota Orihashi, Mana Ihori, Tomohiro Tanaka, Naoki Makishima, Satoshi Suzuki, Saki Mizuno, Nobukatsu Hojo
2025	C	`conf`	Phoneme Overlapping-Aware Pre-Training with External Text Resources for Multi-Talker ASR. ASRU Ryo Masumura, Tomohiro Tanaka, Naoki Makishima, Mana Ihori, Shota Orihashi, Naotaka Kawata, Taiga Yamane, Satoshi Suzuki, Takafumi Moriya
2025	A	`conf`	SOMSRED-SVC: Sequential Output Modeling with Speaker Vector Constraints for Joint Multi-Talker Overlapped ASR and Speaker Diarization. INTERSPEECH Naoki Makishima, Naotaka Kawata, Taiga Yamane, Mana Ihori, Tomohiro Tanaka, Satoshi Suzuki, Shota Orihashi, Ryo Masumura
2025	—	`conf`	Semi-Supervised End-to-End Speech-to-Text Translation with Joint Text-to-Text and Speech-to-Text Decoding. APSIPA Tomohiro Tanaka, Ryo Masumura, Naoki Makishima, Mana Ihori, Shota Orihashi, Satoshi Suzuki, Taiga Yamane
2025	A	`conf`	Unified Audio-Visual Modeling for Recognizing Which Face Spoke When and What in Multi-Talker Overlapped Speech and Video. INTERSPEECH Naoki Makishima, Naotaka Kawata, Taiga Yamane, Mana Ihori, Tomohiro Tanaka, Satoshi Suzuki, Shota Orihashi, Ryo Masumura
2024	—	`conf`	Block Refinement Learning for Improving Early Exit in Autoregressive ASR. APSIPA Naotaka Kawata, Shota Orihashi, Satoshi Suzuki, Tomohiro Tanaka, Mana Ihori, Naoki Makishima, Taiga Yamane, Ryo Masumura
2024	A	`conf`	SOMSRED: Sequential Output Modeling for Joint Multi-talker Overlapped Speech Recognition and Speaker Diarization. INTERSPEECH Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Atsushi Ando, Ryo Masumura
2024	A	`conf`	Unified Multi-Talker ASR with and without Target-speaker Enrollment. INTERSPEECH Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Mana Ihori, Naotaka Kawata, Shota Orihashi, Kazutoshi Shinoda, Taiga Yamane, Saki Mizuno, Keita Suzuki, Satoshi Suzuki, Nobukatsu Hojo, Takafumi Moriya, Atsushi Ando
2023	A*	`conf`	Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff. ICCV Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Sekitoshi Kanai, Naoki Makishima, Atsushi Ando, Ryo Masumura
2023	J	`jnl`	Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff. CoRR Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Sekitoshi Kanai, Naoki Makishima, Atsushi Ando, Ryo Masumura
2023	A	`conf`	End-to-End Joint Target and Non-Target Speakers ASR. INTERSPEECH Ryo Masumura, Naoki Makishima, Taiga Yamane, Yoshihiko Yamazaki, Saki Mizuno, Mana Ihori, Mihiro Uchida, Keita Suzuki, Hiroshi Sato, Tomohiro Tanaka, Akihiko Takashima, Satoshi Suzuki, Takafumi Moriya, Nobukatsu Hojo, Atsushi Ando
2023	J	`jnl`	End-to-End Joint Target and Non-Target Speakers ASR. CoRR Ryo Masumura, Naoki Makishima, Taiga Yamane, Yoshihiko Yamazaki, Saki Mizuno, Mana Ihori, Mihiro Uchida, Keita Suzuki, Hiroshi Sato, Tomohiro Tanaka, Akihiko Takashima, Satoshi Suzuki, Takafumi Moriya, Nobukatsu Hojo, Atsushi Ando
2023	A	`conf`	Joint Autoregressive Modeling of End-to-End Multi-Talker Overlapped Speech Recognition and Utterance-level Timestamp Prediction. INTERSPEECH Naoki Makishima, Keita Suzuki, Satoshi Suzuki, Atsushi Ando, Ryo Masumura
2023	—	`conf`	Multi-region CNN-Transformer for Micro-gesture Recognition in Face and Upper Body. MMAsia Keita Suzuki, Satoshi Suzuki, Ryo Masumura, Atsushi Ando, Naoki Makishima
2023	B	`conf`	OnDA-DETR: Online Domain Adaptation for Detection Transformers with Self-Training Framework. ICIP Satoshi Suzuki, Taiga Yamane, Naoki Makishima, Keita Suzuki, Atsushi Ando, Ryo Masumura
2023	—	`conf`	Text-to-Text Pre-Training with Paraphrasing for Improving Transformer-Based Image Captioning. EUSIPCO Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2022	Misc	`conf`	Customer Satisfaction Estimation Using Unsupervised Representation Learning with Multi-Format Prediction Loss. ICASSP Atsushi Ando, Yumiko Murata, Ryo Masumura, Satoshi Suzuki, Naoki Makishima, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato
2022	A	`conf`	End-to-End Joint Modeling of Conversation History-Dependent and Independent ASR Systems with Multi-History Training. INTERSPEECH Ryo Masumura, Yoshihiro Yamazaki, Saki Mizuno, Naoki Makishima, Mana Ihori, Mihiro Uchida, Hiroshi Sato, Tomohiro Tanaka, Akihiko Takashima, Satoshi Suzuki, Shota Orihashi, Takafumi Moriya, Nobukatsu Hojo, Atsushi Ando
2022	J	`jnl`	Knowledge Transferred Fine-Tuning: Convolutional Neural Network Is Born Again With Anti-Aliasing Even in Data-Limited Situations. IEEE Access Satoshi Suzuki, Shoichiro Takeda, Naoki Makishima, Atsushi Ando, Ryo Masumura, Hayaru Shouno
2022	—	`conf`	On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis. SLT Atsushi Ando, Ryo Masumura, Akihiko Takashima, Satoshi Suzuki, Naoki Makishima, Keita Suzuki, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato
2022	J	`jnl`	On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis. CoRR Atsushi Ando, Ryo Masumura, Akihiko Takashima, Satoshi Suzuki, Naoki Makishima, Keita Suzuki, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato
2022	A	`conf`	Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data. INTERSPEECH Naoki Makishima, Satoshi Suzuki, Atsushi Ando, Ryo Masumura
2022	J	`jnl`	Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data. CoRR Naoki Makishima, Satoshi Suzuki, Atsushi Ando, Ryo Masumura
2022	A	`conf`	Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations. INTERSPEECH Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Ryo Masumura
2022	J	`jnl`	Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations. CoRR Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Ryo Masumura
2021	Misc	`conf`	Audio-Visual Speech Separation Using Cross-Modal Correspondence Loss. ICASSP Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2021	J	`jnl`	Audio-Visual Speech Separation Using Cross-Modal Correspondence Loss. CoRR Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2021	A	`conf`	Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition. Interspeech Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima, Takafumi Moriya, Takanori Ashihara, Shota Orihashi, Naoki Makishima
2021	J	`jnl`	Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition. CoRR Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima, Takafumi Moriya, Takanori Ashihara, Shota Orihashi, Naoki Makishima
2021	A	`conf`	End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning. Interspeech Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima, Shota Orihashi, Naoki Makishima
2021	J	`jnl`	End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning. CoRR Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima, Shota Orihashi, Naoki Makishima
2021	A	`conf`	Enrollment-Less Training for Personalized Voice Activity Detection. Interspeech Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura
2021	J	`jnl`	Enrollment-less training for personalized voice activity detection. CoRR Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura
2021	C	`conf`	Hierarchical Knowledge Distillation for Dialogue Sequence Labeling. ASRU Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura
2021	J	`jnl`	Hierarchical Knowledge Distillation for Dialogue Sequence Labeling. CoRR Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura
2021	Misc	`conf`	Hierarchical Transformer-Based Large-Context End-To-End ASR with Large-Context Knowledge Distillation. ICASSP Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2021	J	`jnl`	Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillation. CoRR Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2021	J	`jnl`	Independent deeply learned matrix analysis with automatic selection of stable microphone-wise update and fast sourcewise update of demixing matrix. Signal Process. Naoki Makishima, Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo
2021	—	`conf`	Large-Context Conversational Representation Learning: Self-Supervised Learning For Conversational Documents. SLT Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2021	J	`jnl`	Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents. CoRR Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2021	J	`jnl`	MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training. CoRR Mana Ihori, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura
2021	Misc	`conf`	MAPGN: Masked Pointer-Generator Network for Sequence-to-Sequence Pre-Training. ICASSP Mana Ihori, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura
2021	A	`conf`	Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation. Interspeech Ryo Masumura, Daiki Okamura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2021	J	`jnl`	Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation. CoRR Ryo Masumura, Daiki Okamura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2021	—	`conf`	Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages. MMAsia Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura
2021	J	`jnl`	Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages. CoRR Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura
2021	A	`conf`	Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks Using Switching Tokens. Interspeech Mana Ihori, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura
2021	J	`jnl`	Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks using Switching Tokens. CoRR Mana Ihori, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura
2020	B	`conf`	Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model. INLG Mana Ihori, Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi
2020	J	`jnl`	Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model. CoRR Mana Ihori, Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi
2020	A	`conf`	Phoneme-to-Grapheme Conversion Based Large-Scale Pre-Training for End-to-End Automatic Speech Recognition. INTERSPEECH Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi
2020	—	`conf`	Unsupervised Domain Adversarial Training in Angular Space for Facial Expression Recognition. APSIPA Akihiko Takashima, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2019	J	`jnl`	Independent Deeply Learned Matrix Analysis for Determined Audio Source Separation. IEEE ACM Trans. Audio Speech Lang. Process. Naoki Makishima, Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hayato Sumino, Shinnosuke Takamichi, Hiroshi Saruwatari, Nobutaka Ono
2019	—	`conf`	Robust Demixing Filter Update Algorithm Based on Microphone-wise Coordinate Descent for Independent Deeply Learned Matrix Analysis. APSIPA Naoki Makishima, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo