mlsanityData to 14 Oct 2026

Preference Optimization for Non-Verbal Vocalization Synthesis

arXiv 2608.24163 ↗First posted 25 Aug 2026eess.AS cs.AI cs.LGcited by 2

On the map: LLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG

Abstract (arXiv)

Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive TTS, but the effectiveness of preference optimization for NV generation remains poorly understood. We systematically study preference optimization for NV-capable TTS, focusing on preference signals, preference-pair construction, and DPO-based optimization objectives. We formulate an NV-aware character error rate (NV-CER) by treating NV tags as distinct output symbols and computing a weighted pinyin-based CER over both verbal and non-verbal content, enabling controllable optimization of NV realization without modifying the underlying optimization algorithm. Experiments on Emilia-NV and the augmented NV-Bench covering 18 NV types reveal how different design choices affect NV realization and lexical fidelity, and establish an effective setup using standard DPO. Objective, LLM-based, and human evaluations provide converging evidence for our findings, offering practical insights into NV-aware post-training for expressive TTS.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 19 of its 23 references that are in the map. First posted on arXiv 25 Aug 2026.

Builds on

19 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Preference Alignment Improves Language Model-Based TTS19 Sep

Other references · 18

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  4. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 288
  5. 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 235
  6. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 172
  7. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 150
  8. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 122
  9. 2026Qwen3-TTS Technical Reportcited by 118
  10. 2024Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimizationcited by 32
  11. 2025NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speechcited by 14
  12. 2025A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understandingcited by 11
6 more
  1. 2026Fish Audio S2 Technical Reportcited by 9
  2. 2024DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguagecited by 6
  3. 2025SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understandingcited by 6
  4. 2025MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speechcited by 6
  5. 2026NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generationcited by 6
  6. 2026Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speechcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challengecited by 1
  2. 2026NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speechcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026NVMOS: Non-Verbal Vocalization Quality Assessment in Speech
  2. 2026Preference Optimization with LALM Feedback for Continuous Autoregressive Non-Verbal Vocalization Generation
  3. 2024Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech
  4. 2024Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
  5. 2025No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS
  6. 2025RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis
  7. 2025SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
  8. 2025VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context