Speech & Audio

Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement Interspeech 2025 MelRe: Vision-Based Mel-Spectrogram Restoration Interspeech 2025 Mental-Perceiver: Audio-Textual Multi-Modal Learning for Estimating Mental Disorders AAAI 2025 MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore ACL 2025 Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models Interspeech 2025 MetaMixSpeech: Meta Task Augmentation for Low-Resource Speech Recognition EMNLP 2025 Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning Interspeech 2025 MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition Interspeech 2025 Mimic Blocker: Self-Supervised Adversarial Training for Voice Conversion Defense with Pretrained Feature Extractors Interspeech 2025 MISP-Meeting: A Real-World Dataset with Multimodal Cues for Long-form Meeting Transcription and Summarization ACL 2025 Mispronunciation Detection Without L2 Pronunciation Dataset in Low-Resource Setting: A Case Study in Finland Swedish Interspeech 2025 MiSTR: Multi-Modal iEEG-to-Speech Synthesis with Transformer-Based Prosody Prediction and Neural Phase Reconstruction Interspeech 2025 Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets EMNLP 2025 Mitigating Language Mismatch in SSL-Based Speaker Anonymization Interspeech 2025 Mitigating Non-Target Speaker Bias in Guided Speaker Embedding Interspeech 2025 Mitigating Overfitting During Speech Foundation Model Fine-tuning: Applications to Dysarthric Speech Detection Interspeech 2025 Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition Interspeech 2025 MMLoRA: Multitask Memory Parameter-Efficient Fine-Tuning for Multimodal SER Interspeech 2025 MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing Interspeech 2025 MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens ACL 2025 “Mm, Wat?” Detecting Other-initiated Repair Requests in Dialogue EMNLP 2025 MockConf: A Student Interpretation Dataset: Analysis, Word- and Span-level Alignment and Baselines ACL 2025 Modality-Agnostic Multimodal Emotion Recognition using a Contrastive Masked Autoencoder Interspeech 2025 Modality-Specific Speech Enhancement and Noise-Adaptive Fusion for Acoustic and Body-Conduction Microphone Framework Interspeech 2025 Model as Loss: A Self-Consistent Training Paradigm Interspeech 2025