https://speech-expert.ru/news/asr-errors-embodied-ai-safety Speech Expert ru 2026-09-01T00:00:00Z When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI https://speech-expert.ru/news/reference-free-forced-alignment-metrics Speech Expert ru 2026-09-01T00:00:00Z Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation https://speech-expert.ru/news/spiking-cochlear-denoising Speech Expert ru 2026-09-01T00:00:00Z Low-Power End-to-End Cochlear Implant Speech Denoising with Spiking Neural Networks https://speech-expert.ru/news/hrtf-spatial-masking-music Speech Expert ru 2026-09-01T00:00:00Z Effects of HRTF Augmentation on Predicted Spatial Release from Masking in Music https://speech-expert.ru/news/audio-transformation-representations Speech Expert ru 2026-09-01T00:00:00Z Exploring the Design Space of Representation Learning for Audio Transformations https://speech-expert.ru/news/vocal-evasion-benchmark Speech Expert ru 2026-09-01T00:00:00Z A Shaky Voice Is Not Always a Dodge: Benchmarking Textual and Vocal Evasion Detection in Earnings Calls https://speech-expert.ru/news/multiparty-turn-taking-cues Speech Expert ru 2026-09-01T00:00:00Z Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness https://speech-expert.ru/news/crosslingual-prosody-similarity Speech Expert ru 2026-09-01T00:00:00Z Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages https://speech-expert.ru/news/audiovisual-prior-dominance Speech Expert ru 2026-09-01T00:00:00Z Compositional Failure in Audio-Visual LLMs: Late-Layer Prior Dominance Under Cross-modal Conflict https://speech-expert.ru/news/subjective-vote-variance-model Speech Expert ru 2026-09-01T00:00:00Z A Mixed-Behavior Vote Model for Multimedia Subjective Quality Votes, Means, and Variances https://speech-expert.ru/news/ood-sound-matching-losses Speech Expert ru 2026-09-01T00:00:00Z Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance https://speech-expert.ru/news/alias-free-oscillator-synchronization Speech Expert ru 2026-09-01T00:00:00Z Alias-Free Oscillator Synchronization via Additive Synthesis https://speech-expert.ru/news/multirate-pdm-speech-processing Speech Expert ru 2026-08-31T00:00:00Z Multirate State Space Models for End-to-End Processing of Pulse Density Modulated Speech Signals https://speech-expert.ru/news/generative-audio-call-audit Speech Expert ru 2026-08-31T00:00:00Z Auditing Generative Audio Calls for Known-Task Audio-LLM Evaluation https://speech-expert.ru/news/sure-speech-evidence-gating Speech Expert ru 2026-08-31T00:00:00Z SURE-Challenge: Evaluating Speech Evidence Before Speech-LLM Generation https://speech-expert.ru/news/affective-audio-generalization-boundaries Speech Expert ru 2026-08-31T00:00:00Z Not all generalisation failures can be bought back: four boundaries in affective audio modelling https://speech-expert.ru/news/voice-cloning-anonymization Speech Expert ru 2026-08-31T00:00:00Z Your Voice Cloning System is Secretly a Voice Anonymizer https://speech-expert.ru/news/audio-llm-information-routing Speech Expert ru 2026-08-31T00:00:00Z Direct or Mediated? Task-Dependent Audio Information Routing in Large Audio Language Models https://speech-expert.ru/news/visual-grounding-crosslingual-keyword Speech Expert ru 2026-08-31T00:00:00Z Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding https://speech-expert.ru/news/speechgym-voice-agent-rl Speech Expert ru 2026-08-31T00:00:00Z SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning https://speech-expert.ru/news/audiospan-long-audio-comprehension Speech Expert ru 2026-08-31T00:00:00Z AudioSpan: Spanning the Duration and Depth of Audio Comprehension https://speech-expert.ru/news/joint-dereverberation-directional-filtering Speech Expert ru 2026-08-31T00:00:00Z GAN-based Joint Dereverberation and Directional Filtering https://speech-expert.ru/news/decay-group-delay-audio-forensics Speech Expert ru 2026-08-31T00:00:00Z Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Sounds https://speech-expert.ru/news/spiky-shape-adaptive-decomposition Speech Expert ru 2026-08-31T00:00:00Z Time-Varying Spiky Wave-Shape Functions for Non-Stationary Signal Decomposition https://speech-expert.ru/news/adaptive-contrastive-avsr Speech Expert ru 2026-08-31T00:00:00Z Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition