mlsanityData to 7 Oct 2026

Imitation Learning for Elder-Facing Speech Synthesis

arXiv 2606.21053 ↗First posted 19 Jun 2026cs.SD cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Language-conditioned policies and VLAs

Abstract (arXiv)

Recent advances in text-to-speech (TTS) synthesis have achieved highly natural and expressive speech generation. However, these systems are designed for general adults and overlook older adults' speech comprehension needs due to age-related sensory and cognitive decline. Prior work involves older adults by collecting preference feedback to tune model parameters. However, obtaining sufficient preference data is costly and difficult, as older adults quickly become fatigued during collection. In this paper, we propose a novel imitation learning (IL) framework to learn TTS models from expert demonstrations. We further improve Group Relative Policy Optimization (GRPO) with two-stage on-policy reward learning (OPRL) to mitigate reward hacking under limited supervision from expert demonstration. Experimental results show that GRPO w/ OPRL outperforms GRPO and supervised baselines in objective and subjective metrics. Audio samples are available at https://dongru1.github.io/demo/im-efss

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data. Builds on 24 of its 41 references that are in the map. First posted on arXiv 19 Jun 2026.

Builds on

24 of 41 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2016Layer Normalizationcited by 5,579
  4. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  5. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  6. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  7. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  8. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  9. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 118
  10. 2023CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Maskingcited by 95
  11. 2024SpeechAlign: Aligning Speech Generation to Human Preferencescited by 45
  12. 2019Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesiscited by 44
12 more
  1. 2024Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimizationcited by 31
  2. 2025Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedbackcited by 26
  3. 2025F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimizationcited by 24
  4. 2024Preference Alignment Improves Language Model-Based TTScited by 21
  5. 2025Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignmentcited by 18
  6. 2021Imitation Learning by Reinforcement Learningcited by 17
  7. 2024Fine-Tuning Language Models with Reward Learning on Policycited by 15
  8. 2025WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotationcited by 8
  9. 2025TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systemscited by 7
  10. 2025DrawSpeech: Expressive Speech Synthesis Using Prosodic Sketches as Control Conditionscited by 6
  11. 2025Group Relative Policy Optimization for Text-to-Speech with Large Language Modelscited by 6
  12. 2025Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedbackcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation
  2. 2025Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scale
  3. 2024Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
  4. 2025No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS
  5. 2026When Synthetic Speech Is All You Have: Better Call GRPO
  6. 2025DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis
  7. 2026GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model
  8. 2025Explore the Reinforcement Learning for the LLM based ASR and TTS system