https://speech-expert.ru/news/speech-synthesizers-deceive-people Speech Expert ru 2026-08-24T00:00:00Z Tracking the Trend in How Speech Synthesizers Deceive People https://speech-expert.ru/news/asr-benchmark-optimization Speech Expert ru 2026-08-24T00:00:00Z Towards Quantifying Benchmark Optimization in ASR Models https://speech-expert.ru/news/nape-next-audio-patch-embedding Speech Expert ru 2026-08-24T00:00:00Z Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners https://speech-expert.ru/news/ear-vae2-phase-aware-spectral Speech Expert ru 2026-08-24T00:00:00Z Fourier is Frontier: Frequency-Aware Autoencoding for High-Fidelity Music Reconstruction https://speech-expert.ru/news/hear2act-prosody-action-benchmark Speech Expert ru 2026-08-24T00:00:00Z Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does https://speech-expert.ru/news/prosody-underuse-causal-audio-llm Speech Expert ru 2026-08-24T00:00:00Z Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models