SpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences
cs.AI, cs.SD
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/snakers4/silero-vad
Sources
- Critique-out-Loud Reward Models
- Constitutional AI: Harmlessness from AI Feedback
- Kimi-Audio Technical Report
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Qwen3-TTS Technical Report
- WavReward: Spoken Dialogue Models With Generalist Reward Evaluators
- RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
- UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
- GSRM: Generative Speech Reward Model for Speech RLHF
- Qwen3-ASR Technical Report
- Self-Taught Evaluators
- Step-Audio 2 Technical Report
- Qwen2.5-Omni Technical Report
- Qwen3-Omni Technical Report
- MOSS-Audio Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
- SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems