Decoupled-Live-ProsodyJudge (D-LPJ), a cost-effective pairwise evaluator distilled from Gemini into Qwen3-Omni, and a novel span-local GRPO strategy that applies normalized advantages strictly to their corresponding rationale spans.
Abstract
Evaluating live streaming speech synthesis (TTS) requires assessing fine-grained, highly expressive prosody such as emotion, intonation, and energy which traditional MOS predictors fail to capture. While proprietary Large Language Models (LLMs) like Gemini can evaluate these aspects, they are too costly for massive inference and reinforcement learning feedback. To address this, we first introduce Live-ProsodyJudge (LPJ), a cost-effective pairwise evaluator distilled from Gemini into Qwen3-Omni. However, we identify a critical flaw in standard multi-dimensional evaluation: verdict coupling. The judge tends to lazily align all individual dimension scores with its overall preference, collapsing a rich multi-dimensional rubric into a single preference bit. To resolve this, we further propose Decoupled-Live-ProsodyJudge (D-LPJ). D-LPJ eliminates the overall verdict target to prevent blind following, masks uncertain pair-dimensions during Supervised Fine-Tuning(SFT), and introduces a novel span-local GRPO strategy that applies normalized advantages strictly to their corresponding rationale spans. Evaluated on highly curated human-annotated test sets, 10 sample balanced-order LPJ achieves higher point accuracy than a single Gemini call, while D-LPJ successfully produces independent,decoupled dimension judgments. Furthermore, in a Best-of-8 TTS candidate selection tournament, the LPJ-selected utterance falls within the human top-3 in 85.29% of high-confidence cases, demonstrating its efficacy for fine-grained TTS preference optimization.
An NVV-aware DiTAR system that models continuous speech latents, encodes the 16 target NVV categories as dedicated to- kens, and adapts stop prediction to distinguish mid-utterance vocalizations from utterance boundaries is developed.
Zi-Yu Zhang, Yun Chen, Tai-Hui Wang et al.· arXiv.org· 1 citation
AWED, a word-level emission-delay metric defined relative to the acoustic end of each word, is introduced and post-train a DSM recognizer with GRPO under a reward that scores transcription accuracy and measured delay jointly, advancing the accuracy--latency Pareto frontier of streaming ASR without architectural change.
Generative speech enhancement models can produce cleaner and more natural-sounding speech than conventional discriminative approaches, but may hallucinate by changing speech content or speaker identity, even with transcript conditioning. We present AuraSE, a flow-matching framework that addresses hallucination through...
Ying Shen, Yao Qian, Yuxuan Hu et al.· 0 citations
Recent speech enhancement systems combine self-attention and Mamba to capture global interactions and long-range dependencies. Yet these hybrids usually operate as sequence mixers and do not explicitly exploit harmonic periodicity, a strong cue for preserving voiced speech under noise. Perceptual optimization poses ano...
Shang-Fu Chen, Szu-Wei Fu, Sung-Feng Huang et al.· 0 citations
A layer-calibrated aggregation variant that applies per-layer adapters before pooling is evaluated, which improves the robustness of multi-layer fusion and narrows the gap to full fine-tuning while keeping the backbone frozen.
A. Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva et al.· Interspeech· 0 citations
An LLM-based framework that performs discrete emotion recognition and Valence-Arousal-Dominance dimensional evaluation on IEMOCAP, incorporating acoustic cues as natural language descriptions following the SpeechCueLLM approach is proposed.
Yu-Tong Hu, Jin-Ho D. Choi· arXiv.org· 0 citations