https://speech-expert.ru/news/binaural-cue-preservation-loss Speech Expert ru 2026-08-19T00:00:00Z A Novel Binaural Cue Preservation Loss for DNN-Based Binaural Speech Enhancement https://speech-expert.ru/news/diffm2a-geometry-adaptive-ambisonics Speech Expert ru 2026-08-19T00:00:00Z Geometry-adaptive Ambisonic encoding for sparse microphone arrays of variable topology using physics-informed diffusion https://speech-expert.ru/news/speaker-normalized-semantic-speech-tokens Speech Expert ru 2026-08-19T00:00:00Z Speaker-Normalized Semantic Speech Tokens via Iterative S2U-T2U Refinement https://speech-expert.ru/news/inspire-instruction-aware-speech-retrieval Speech Expert ru 2026-08-19T00:00:00Z INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval https://speech-expert.ru/news/speech-enhancement-rtmri-assessment Speech Expert ru 2026-08-19T00:00:00Z Navigating Speech Enhancement for Real-Time MRI: A Systematic Assessment of Signal Quality, Source Preservation, and Downstream Tasks https://speech-expert.ru/news/speech-prediction-active-suppression Speech Expert ru 2026-08-19T00:00:00Z Feedforward Active Speech Suppression Based on Time Series Prediction of Speech Signals Using Neural Networks https://speech-expert.ru/news/duplexgen-synthetic-dialogue-speech Speech Expert ru 2026-08-19T00:00:00Z DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech https://speech-expert.ru/news/cached-llm-probability-speech-recognition Speech Expert ru 2026-08-19T00:00:00Z Cached LLM Probability Retrieval for Speech Recognition https://speech-expert.ru/news/null-token-message-free-hallucination Speech Expert ru 2026-08-19T00:00:00Z The Null Token Knows: Reducing Message-Free Hallucination in ASR and NMT https://speech-expert.ru/news/iterative-self-learning-expressive-tts Speech Expert ru 2026-08-19T00:00:00Z Iterative Self-Learning for Expressive Text-to-Speech Synthesis https://speech-expert.ru/news/arena-audio-language-model-red-teaming Speech Expert ru 2026-08-19T00:00:00Z ARENA: Automated Red-Teaming for Large Audio Language Models https://speech-expert.ru/news/separate-first-then-associate-real-world-avse Speech Expert ru 2026-08-19T00:00:00Z Separate First, Then Associate: A Two-Stage Approach for Real-World Audio-Visual Speech Enhancement https://speech-expert.ru/news/singer-informed-vocal-separation-duet-mixtures Speech Expert ru 2026-08-18T00:00:00Z Singer-Informed Vocal Source Separation for Multi-Singer Music Mixtures https://speech-expert.ru/news/at-add-all-type-audio-deepfake-challenge Speech Expert ru 2026-08-18T00:00:00Z AT-ADD: All-Type Audio Deepfake Detection Challenge Summary https://speech-expert.ru/news/mlc-slm-leading-silence-synthetic-supervision Speech Expert ru 2026-08-18T00:00:00Z Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge https://speech-expert.ru/news/device-agnostic-ambisonics-room-impulse-diffusion Speech Expert ru 2026-08-18T00:00:00Z Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Model https://speech-expert.ru/news/voicechat-tts-continuous-interruption-aware-synthesis Speech Expert ru 2026-08-18T00:00:00Z VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents https://speech-expert.ru/news/trajectory-dynamics-audio-deepfake-detection Speech Expert ru 2026-08-18T00:00:00Z Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection https://speech-expert.ru/news/streamhear-streaming-speech-recognition-pseudolabels Speech Expert ru 2026-08-18T00:00:00Z StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition https://speech-expert.ru/news/semantic-aware-audio-language-model-fairness Speech Expert ru 2026-08-18T00:00:00Z Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation https://speech-expert.ru/news/voicedesigner-text-to-voice-generation-editing Speech Expert ru 2026-08-18T00:00:00Z VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation