Speech & Audio

Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025 ACL 2025 SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning ACL 2025 SING: Spatial Context in Large Language Model for Next-Gen Wearables ICML 2025 SiTa - Sinhala and Tamil Speaker Diarization Dataset in the Wild COLING 2025 Skip-Salsa: Skip Synchronous Fusion of ASR LLM Decoders Interspeech 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 SLASH: Self-Supervised Speech Pitch Estimation Leveraging DSP-derived Absolute Pitch Interspeech 2025 SMARTMOS: Modeling Subjective Audio Quality Evaluation for Real-Time Applications Interspeech 2025 SNR-Aligned Consistent Diffusion for Adaptive Speech Enhancement Interspeech 2025 SOMSRED-SVC: Sequential Output Modeling with Speaker Vector Constraints for Joint Multi-Talker Overlapped ASR and Speaker Diarization Interspeech 2025 Sounding Like a Winner? Prosodic Differences in Post-Match Interviews Interspeech 2025 SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction Interspeech 2025 SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding CVPR 2025 Soundwave: Less is More for Speech-Text Alignment in LLMs ACL 2025 Source Verification for Speech Deepfakes Interspeech 2025 SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant Interspeech 2025 SPACER: A Parallel Dataset of Speech Production And Comprehension of Error Repairs NAACL 2025 SPARC: An AI-Based Speech Processing and Real-Time Correction System IJCAI 2025 SparQLe: Speech Queries to Text Translation Through LLMs ACL 2025 Spatially Weighted Contrastive Learning for Robust Sound Source Localization Interspeech 2025 Spatio-Spectral Diarization of Meetings by Combining TDOA-based Segmentation and Speaker Embedding-based Clustering Interspeech 2025 SPCODEC: Split and Prediction for Neural Speech Codec Interspeech 2025 Speaker-agnostic Emotion Vector for Cross-speaker Emotion Intensity Control Interspeech 2025 Speaker-Aware Multi-Task Learning for Speech Emotion Recognition Interspeech 2025