https://speech-expert.ru/news/common-measure-communication-speech-bci Speech Expert ru 2026-09-04T00:00:00Z A Common Measure of Communication for Speech Brain-Computer Interfaces https://speech-expert.ru/news/vibevoice-asr-streaming-technical-report Speech Expert ru 2026-09-04T00:00:00Z VibeVoice-ASR-Streaming Technical Report https://speech-expert.ru/news/dry-contact-ear-eeg-adaptive-motion-artifact-cancellation Speech Expert ru 2026-09-04T00:00:00Z A Dry-Contact Ear-EEG System With Continuous Electrode-Skin Impedance Mismatch Monitoring for Motion Artifact Cancellation Using DRL Stimulus https://speech-expert.ru/news/choosing-peft-per-patient-dysarthric-asr Speech Expert ru 2026-09-04T00:00:00Z Choosing a PEFT Variant for Per-Patient Dysarthric ASR: A Single-Speaker Case Study on Two ASR Bases https://speech-expert.ru/news/arft-synchronized-rf-acoustic-positioning-dataset Speech Expert ru 2026-09-04T00:00:00Z ARFT: A Synchronized Multimodal RF-Acoustic Dataset for Positioning in Distributed Environments https://speech-expert.ru/news/scalable-direction-following-tts-pseudo-triplets Speech Expert ru 2026-09-04T00:00:00Z Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction https://speech-expert.ru/news/vaani-noise-event-dataset Speech Expert ru 2026-09-04T00:00:00Z VAANI Noise Event Dataset: A curated spontaneous speech dataset annotated with timestamps for noise events https://speech-expert.ru/news/removing-speech-keeping-activities-privacy-firewall Speech Expert ru 2026-09-04T00:00:00Z Removing Speech, Keeping Activities: A Privacy Firewall for Acoustic Sensing in Assisted Living https://speech-expert.ru/news/soniccaps-diverse-audio-captioning-retrieval Speech Expert ru 2026-09-04T00:00:00Z SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval https://speech-expert.ru/news/auditory-illusion-benchmark-audio-language-models Speech Expert ru 2026-09-04T00:00:00Z Auditory Illusion Benchmark for Large Audio Language Models https://speech-expert.ru/news/sensing-bone-conducted-speech-with-earbuds Speech Expert ru 2026-09-04T00:00:00Z Sensing Bone-Conducted Speech with Earbuds https://speech-expert.ru/news/avert-audio-verified-spoken-dialogue-state-tracking Speech Expert ru 2026-09-04T00:00:00Z AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking https://speech-expert.ru/news/speakpay-nepali-financial-speech-recognition Speech Expert ru 2026-09-04T00:00:00Z SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition https://speech-expert.ru/news/hearing-the-whispers-tts-membership-inference Speech Expert ru 2026-09-04T00:00:00Z Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models https://speech-expert.ru/news/tag-bench-temporal-audio-grounding Speech Expert ru 2026-09-03T00:00:00Z TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models https://speech-expert.ru/news/soft-speaker-injection-multitalker-asr Speech Expert ru 2026-09-03T00:00:00Z Soft Posterior Speaker Injection for Multi-Talker Speech Recognition https://speech-expert.ru/news/uncertainty-aware-speaker-verification-backend Speech Expert ru 2026-09-03T00:00:00Z A Unified Uncertainty-Aware Back-End for Speaker Verification: Scoring, Normalization, and Calibration https://speech-expert.ru/news/phrase-localized-accent-control-tts Speech Expert ru 2026-09-03T00:00:00Z Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech https://speech-expert.ru/news/abse-net-open-fit-hearing-aids Speech Expert ru 2026-09-03T00:00:00Z ABSE-NET: A Lightweight Neural Model for Active Binaural Speech Enhancement in Open-Fit Hearing Aids https://speech-expert.ru/news/passive-fingerprints-speech-deepfake-attribution Speech Expert ru 2026-09-03T00:00:00Z Perceptible or Not? Diagnosing Passive Fingerprints for Speech Deepfake Attribution https://speech-expert.ru/news/heard-not-heeded-paralinguistic-loss Speech Expert ru 2026-09-03T00:00:00Z Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models https://speech-expert.ru/news/voicelongmemeval-paralinguistic-memory Speech Expert ru 2026-09-03T00:00:00Z VoiceLongMemEval: Do Assistants Remember How You Sounded? https://speech-expert.ru/news/bimtokenizer-low-bitrate-speech-codec Speech Expert ru 2026-09-03T00:00:00Z BiMTokenizer: Preserving Semantic-Acoustic Balance in Low-Bitrate Speech Tokenization via Bidirectional State-Space Modeling https://speech-expert.ru/news/u-past-phase-aware-speech-enhancement Speech Expert ru 2026-09-03T00:00:00Z U-PAST: A Phase-Aware Audio Spectrogram Transformer-U-Net for Single-Channel Speech Enhancement https://speech-expert.ru/news/cleaner-speech-weaker-ad-generalization Speech Expert ru 2026-09-03T00:00:00Z Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection https://speech-expert.ru/news/xvae-wmt-wavelet-source-separation Speech Expert ru 2026-09-03T00:00:00Z XVAE-WMT: Explainable Wavelet-Temporal Variational Autoencoder for Blind Source Separation of Heart and Lung Sounds