Synthesis

SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models AAAI 2025 SEED: Speaker Embedding Enhancement Diffusion Model Interspeech 2025 Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversion AAAI 2025 SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation IJCAI 2025 SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning ACL 2025 Simple and Effective Content Encoder for Singing Voice Conversion via SSL-Embedding Dimension Reduction Interspeech 2025 SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation ACL 2025 SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning ACL 2025 Slamming: Training a Speech Language Model on One GPU in a Day ACL 2025 SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training ACL 2025 SMARTMOS: Modeling Subjective Audio Quality Evaluation for Real-Time Applications Interspeech 2025 SNR-Aligned Consistent Diffusion for Adaptive Speech Enhancement Interspeech 2025 SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding CVPR 2025 SPARC: An AI-Based Speech Processing and Real-Time Correction System IJCAI 2025 Speaker-agnostic Emotion Vector for Cross-speaker Emotion Intensity Control Interspeech 2025 SpeechDialogueFactory: A Framework for Natural Speech Dialogue Generation Interspeech 2025 Speech Enhancement based on cascaded two flows Interspeech 2025 Speech Enhancement with Dual-path Multi-Channel Linear Prediction Filter and Multi-norm Beamforming Interspeech 2025 SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods ACL 2025 Speech-guided Grapheme-to-Phoneme Conversion for Cantonese Text-to-Speech Interspeech 2025 SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Interspeech 2025 SpeechSEC: A Unified Multi-Task Framework for Speech Synthesis, Editing, and Continuation Interspeech 2025 Speech Watermarking with Discrete Intermediate Representations AAAI 2025 SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models ACL 2025 Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech Interspeech 2025