Zejun Ma

MMSearch-R1: Incentivizing LMMs to Search ACL 2026 Audio-centric Video Understanding Benchmark without Text Shortcut EMNLP 2025 Improving LLM Video Understanding with 16 Frames Per Second ICML 2025 LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale CVPR 2025 LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models ICLR 2025 video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model ICML 2025 Can Large Language Models Understand Spatial Audio? Interspeech 2024 Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis ICLR 2024 MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning Interspeech 2024 PolyVoice: Language Models for Speech to Speech Translation ICLR 2024 Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis ICLR 2024 RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency ECCV 2024 SALMONN: Towards Generic Hearing Abilities for Large Language Models ICLR 2024 video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models ICML 2024 AudioQR: Deep Neural Audio Watermarks For QR Code IJCAI 2023 Disentangling the Contribution of Non-native Speech in Automated Pronunciation Assessment Interspeech 2023 GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech Interspeech 2023 Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition Interspeech 2023 Knowledge Distillation Approach for Efficient Internal Language Model Estimation Interspeech 2023 Language-specific Boundary Learning for Improving Mandarin-English Code-switching Speech Recognition Interspeech 2023 Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring Interspeech 2023 Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition Interspeech 2023 S2CD: Self-heuristic Speaker Content Disentanglement for Any-to-Any Voice Conversion Interspeech 2023 StyleS2ST: Zero-shot Style Transfer for Direct Speech-to-speech Translation Interspeech 2023 Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer Interspeech 2023 Virtual Try-On with Pose-Garment Keypoints Guided Inpainting ICCV 2023 A Transfer and Multi-Task Learning based Approach for MOS Prediction Interspeech 2022 BiFSMN: Binary Neural Network for Keyword Spotting IJCAI 2022 Bring dialogue-context into RNN-T for streaming ASR Interspeech 2022 Improving Contextual Representation with Gloss Regularized Pre-training NAACL 2022 Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR Interspeech 2022 Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire Interspeech 2022 Towards high-fidelity singing voice conversion with acoustic reference and contrastive predictive coding Interspeech 2022 Zero-Shot Audio Source Separation through Query-Based Learning from Weakly-Labeled Data AAAI 2022 Attention-Based Cross-Modal Fusion for Audio-Visual Voice Activity Detection in Musical Video Streams Interspeech 2021 Emitting Word Timings with HMM-Free End-to-End System in Automatic Speech Recognition Interspeech 2021 Fine-Grained Prosody Modeling in Neural Speech Synthesis Using ToBI Representation Interspeech 2021 HMM-Free Encoder Pre-Training for Streaming RNN Transducer Interspeech 2021