A cue-coverage reward plus a modality-token KL penalty makes multimodal emotion-reasoning models cite more real visual/audio evidence and hallucinate less, with reported SoTA on emotion benchmarks.
Mm-tts: A unified framework for multimodal, prompt-induced emotional text-to- speech synthesis
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
AgentSteerTTS proposes a multi-agent framework with adversarial disentanglement, dual-stream anchoring via acoustic prototypes, and fast-slow feedback to achieve intent-faithful expressive TTS for composite instructions.
A two-stage static-then-dynamic prompt selection strategy using prosodic features, LLM coherence scores, and similarity metrics improves emotion intensity and speaker consistency in zero-shot TTS.
citing papers explorer
-
Omni-Perception Policy Optimization for Multimodal Emotion Reasoning
A cue-coverage reward plus a modality-token KL penalty makes multimodal emotion-reasoning models cite more real visual/audio evidence and hallucinate less, with reported SoTA on emotion benchmarks.
-
AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
AgentSteerTTS proposes a multi-agent framework with adversarial disentanglement, dual-stream anchoring via acoustic prototypes, and fast-slow feedback to achieve intent-faithful expressive TTS for composite instructions.
-
Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS
A two-stage static-then-dynamic prompt selection strategy using prosodic features, LLM coherence scores, and similarity metrics improves emotion intensity and speaker consistency in zero-shot TTS.