The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces Corrective Forcing (CoF), a post‑training method that aligns diffusion and flow generative models for speech enhancement by training them on self‑generated rollout states. CoF corrects predictions toward ground truth under dynamic sampling schedules and regularizes local evolution with counterfactual transitions, applying a unified objective across both model types. Experiments on SB‑VE and OT‑CFM show improved perceptual quality, reconstruction fidelity, and robustness to varying sampling steps.
arXiv:2607. 03134v1 Announce Type: cross Abstract: Recent research expands beyond binary anti-spoofing with the emergence of Source Tracing, the task of identifying the specific generative origins of synthetic speech.
arXiv:2604. 19635v2 Announce Type: replace-cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications.
arXiv:2601. 09239v5 Announce Type: replace-cross Abstract: Speech tokenizers are a key building block of fully discrete Speech LLMs.
arXiv:2607. 09833v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems have achieved high accuracy with transformer-based models, enabling deployment in critical applications.
The paper introduces Grounded Generative Speech Recognition (GSR), redefining speech recognition as generating semantically grounded text rather than a single transcript. It defines a grounded reformulation space and a four-level hierarchy of reformulation capabilities, and presents GSR-Bench, a comprehensive benchmark covering diverse scenarios such as meeting transcription, cross-dialect translation, and robustness to silence or noise. The authors also develop a multi-dimensional evaluation framework that combines speech grounding assessment with LLM-based semantic judgment, validated by human preference studies, and analyze trade-offs and failure modes across various ASR architectures.