← Authors

Naoki Makishima

16 papers · 2020–2026 · 3 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (28) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (3) 🀝 Dynamic Duo (15) πŸ† Keyword Champion (2) πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (15) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (77)

Conferences

INTERSPEECH (13) AAAI (2) ICCV (1)

Top co-authors

Ryo Masumura (16) Tomohiro Tanaka (13) Mana Ihori (13) Shota Orihashi (11) Akihiko Takashima (8) Satoshi Suzuki (8) Atsushi Ando (7) Takafumi Moriya (5) Saki Mizuno (4) Nobukatsu Hojo (4)

Research topics

Speech & Audio (2)

Keywords

automatic speech recognition (7) autoregressive modeling (3) overlapped speech (3) speaker verification (2) autoregressive model (2) joint modeling (2) end-to-end automatic speech recognition (2) multi-talker speech recognition (2) multi-talker speech (2) semi-supervised learning (2) model robustness (1) speaker embedding (1) fine-grained classification (1) multi-task learning (1) contrastive learning (1) adversarial training (1) fine-grained recognition (1) geometric structure (1) multimodal learning (1) speaker diarization (1)

Papers

Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models AAAI 2026
Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level Scores AAAI 2025
SOMSRED: Sequential Output Modeling for Joint Multi-talker Overlapped Speech Recognition and Speaker Diarization INTERSPEECH 2024
Unified Multi-Talker ASR with and without Target-speaker Enrollment INTERSPEECH 2024
End-to-End Joint Target and Non-Target Speakers ASR INTERSPEECH 2023
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff ICCV 2023
Joint Autoregressive Modeling of End-to-End Multi-Talker Overlapped Speech Recognition and Utterance-level Timestamp Prediction INTERSPEECH 2023
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations INTERSPEECH 2022
Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data INTERSPEECH 2022
End-to-End Joint Modeling of Conversation History-Dependent and Independent ASR Systems with Multi-History Training INTERSPEECH 2022
Enrollment-Less Training for Personalized Voice Activity Detection INTERSPEECH 2021
End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning INTERSPEECH 2021
Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition INTERSPEECH 2021
Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation INTERSPEECH 2021
Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks Using Switching Tokens INTERSPEECH 2021
Phoneme-to-Grapheme Conversion Based Large-Scale Pre-Training for End-to-End Automatic Speech Recognition INTERSPEECH 2020