Speech & Audio

From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech CVPR 2025 From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology Interspeech 2025 From Pretraining to Performance: Benchmarking Self-Supervised Speech Models for Interspeech-25 SER Challenge Interspeech 2025 From Scarcity to Sufficiency: Speech Recognition Pipeline for Zero-resource Language Interspeech 2025 From Sharpness to Better Generalization for Speech Deepfake Detection Interspeech 2025 From Static to Dynamic: Enhancing AAC with Generative Imagery and Zero-Shot TTS Interspeech 2025 From Talking and Listening Devices to Intelligent Communicative Machines Interspeech 2025 From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition EMNLP 2025 From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data Interspeech 2025 FROST-EMA: Finnish and Russian Oral Speech Dataset of Electromagnetic Articulography Measurements with L1, L2 and Imitated L2 Accents Interspeech 2025 FSboard: Over 3 Million Characters of ASL Fingerspelling Collected via Smartphones CVPR 2025 FT-Boosted SV: Towards Noise Robust Speaker Verification for English Speaking Classroom Environments Interspeech 2025 Fully End-to-end Streaming Open-vocabulary Keyword Spotting with W-CTC Forced Alignment Interspeech 2025 FUSE-MOS: Fusion of Speech Embeddings for MOS Prediction with Uncertainty Quantification Interspeech 2025 FUSE: Universal Speech Enhancement using Multi‐Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Interspeech 2025 Gender Bias in Instruction-Guided Speech Synthesis Models NAACL 2025 Generalizable Audio Spoofing Detection using Non-Semantic Representations Interspeech 2025 Generating Consistent Prosodic Patterns from Open-Source TTS Systems Interspeech 2025 Generative Annotation for ASR Named Entity Correction EMNLP 2025 Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations ACL 2025 GenPTQ: Green Post-Training Quantization for Large-Scale ASR Models with Mixed-Precision Bit Allocation EMNLP 2025 Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining NAACL 2025 GigaAM: Efficient Self-Supervised Learner for Speech Recognition Interspeech 2025 GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement ACL 2025 GLCLAP: A Novel Contrastive Learning Pre-trained Model for Contextual Biasing in ASR Interspeech 2025