arXiv AI
Same Words, Different Judgments: How Preferences Vary Across Modalities
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Aug 21
VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
arXiv:2608. 18607v2 Announce Type: replace Abstract: Using reinforcement learning to post-train joint video-audio generation models requires a reward signal.
arXiv AI
Oct 19
SpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences
SpeechCritic learns a diagnostic speech judge from only about 300 human-labeled comparisons, calibrating a frontier audio-language model with non-binding hints that select acoustic measurements agreeing with human judgments. The approach improves dimension-level agreement by 6.3 points and reduces mismatch in Tie rates by 10.4 points, and training a 7B judge with SFT, OPD, and RL yields distinct behaviors, with RL producing more specific rationales. The method works across language pairs, demonstrating a path from limited human preferences to a diagnostic speech judge.
arXiv Computation and Language
Sep 1
When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models
arXiv:2608.31035v1 Announce Type: new Abstract: Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptu...
arXiv Machine Learning
Sep 15
The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech
arXiv:2609.13150v1 Announce Type: cross Abstract: Reference-free quality predictors such as UTMOS, DNSMOS and SCOREQ are the de facto automatic evaluators for text-to-speech (TTS) and are increasingl...
arXiv Machine Learning
Jun 24
Aligning Audio Captions with Human Preferences
arXiv:2509. 14659v3 Announce Type: replace-cross Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios.
arXiv Computation and Language
Sep 30
HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech
arXiv:2606.28249v2 Announce Type: replace-cross Abstract: Recently, Large Language Model (LLM)-based Text-to-Speech (TTS) models have achieved remarkable naturalness. However, the standard Supervised...