Speech Processing

Online AV-CrossNet: a Causal and Efficient Audiovisual System for Speech Enhancement and Target Speaker Extraction Interspeech 2025 On the Design of a Robust Superdirective Beamformer and Topology Parameter Optimization with Frustum-Shaped Microphone Arrays Featuring Multiple Rings Interspeech 2025 On the Language and Gender Biases in PSTN, VoIP and Neural Audio Codecs Interspeech 2025 Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge Interspeech 2025 PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogue EMNLP 2025 PAST: Phonetic-Acoustic Speech Tokenizer Interspeech 2025 PeriodCodec: A Pitch-Controllable Neural Audio Codec Using Periodic Signals for Singing Voice Synthesis Interspeech 2025 Pick and Summarize: Integrating Extractive and Abstractive Speech Summarization Interspeech 2025 Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction Interspeech 2025 Power Spectral Density Estimation for Acoustic Source Separation Using A Spherical Microphone Array Interspeech 2025 Private kNN-VC: Interpretable Anonymization of Converted Speech Interspeech 2025 Probing the Robustness Properties of Neural Speech Codecs Interspeech 2025 Pseudo Labels-based Neural Speech Enhancement for the AVSR Task in the MISP-Meeting Challenge Interspeech 2025 Quadruple Path Modeling with Latent Feature Transfer for Permutation-free Continuous Speech Separation Interspeech 2025 QUADS: Quantized Distillation Framework for Efficient Speech Language Understanding Interspeech 2025 Queer Waves: A German Speech Dataset Capturing Gender and Sexual Diversity from Podcasts and YouTube Interspeech 2025 RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval Interspeech 2025 Real-Time Diffusion Buffer for Speech Enhancement On A Laptop Interspeech 2025 Real-time TSE demonstration via SoundBeam with KD Interspeech 2025 REAL-T: Real Conversational Mixtures for Target Speaker Extraction Interspeech 2025 Reconstruction of the Complete Vocal Tract Contour Through Acoustic to Articulatory Inversion Using Real-Time MRI Data Interspeech 2025 Representing Speech Through Autoregressive Prediction of Cochlear Tokens Interspeech 2025 ReSepNet: A Unified-Light Model for Recursive Speech Separation with Unknown Speaker Count Interspeech 2025 REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion Interspeech 2025 Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling Interspeech 2025