Speech & Audio

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective Interspeech 2025 DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech AAAI 2025 DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech Interspeech 2025 DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model Interspeech 2025 DiffEmotionVC: A Dual-Granularity Disentangled Diffusion Framework for Any-to-Any Emotional Voice Conversion Interspeech 2025 Differentiable K-means for Fully-optimized Discrete Token-based ASR Interspeech 2025 Differentiable Reward Optimization for LLM based TTS system Interspeech 2025 Different Speech Translation Models Encode and Translate Speaker Gender Differently ACL 2025 DiffMV-ETS: Diffusion-based Multi-Voice Electromyography-to-Speech Conversion using Speaker-Independent Speech Training Targets Interspeech 2025 DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles COLING 2025 Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency Interspeech 2025 Directional Speech Recognition with Full-Duplex Capability Interspeech 2025 Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses Interspeech 2025 Direct-path Relative Harmonic Coefficients Detection for Multi-source Direction-of-Arrival Estimation in Reverberant Environments Interspeech 2025 Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion Interspeech 2025 Discovering Directions of Uncertainty in Speech Inpainting Interspeech 2025 Discrete Audio Representations for Automated Audio Captioning Interspeech 2025 Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data Interspeech 2025 Disentangling Dual-Encoder Masked Autoencoder for Respiratory Sound Classification Interspeech 2025 Disentangling Speaker and Content in Pre-trained Speech Models with Latent Diffusion for Robust Speaker Verification Interspeech 2025 Distilling a speech and music encoder with task arithmetic Interspeech 2025 Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment NAACL 2025 DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation ICML 2025 DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility NAACL 2025 DLF-EEND: Dynamic Layer Fusion for End-to-End Speaker Diarization Interspeech 2025