- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes InstructTTS-OPD, a framework for improving instruction-following TTS through on-policy distillation. It trains separate GRPO teachers for instruction following, intelligibility, and speech quality, then distills their outputs into a student using dense velocity-field supervision. Domain routing and conflict-aware velocity fusion are introduced to reduce interference between objectives.
Critical strengths
- The paper addresses a practical challenge in instruction-following TTS: balancing instruction adherence, intelligibility, and speech quality during post-training.
- On-policy distillation provides a reasonable way to transfer knowledge from specialized teachers without directly combining potentially conflicting rewards.
- The reward analysis is thoughtful. The dialect experiment shows a concrete failure mode: optimizing Mandarin ASR scores can encourage the model to ignore the requested dialect.
Critical weaknesses
- The human study in Appendix D compares only against the base model. It therefore does not establish a perceptual advantage over GRPO, particularly given the small DNSMOS improvement.
- The demonstrated scope is limited to one DiTAR-based model. Although Table 4 shows IF improvements across six subsets, the joint gains in IF, intelligibility, and quality are evaluated mainly on zh_DSD. Whether these gains hold more broadly remains unclear.
- The IF reward model is validated through checkpoint-level correlation with Gemini. This does not establish the reliability of its individual judgments, especially when distinguishing outputs generated for the same instruction.
Questions for authors
- Could you report the number of prompts and listeners for the human study in Appendix D? Could you also include scalar-reward GRPO and evaluate instruction adherence and naturalness separately?
- Could you report the IF reward model’s utterance-level agreement with Gemini and accuracy against human annotations on an independent test set, with results broken down by instruction category?
- Does the GRPO baseline use equivalent domain-specific reward handling? How do the tuning budget and total training cost compare with the full teacher-training and distillation pipeline?
Please start the discussion on the rebuttals
Dear Reviewers,
Thanks a lot for your help reviewing this submission! We have received the rebuttals of the authors, so I would like to hear everyone's opinion on the authors' rebuttal to help me form my final meta-review and recommendation for this paper.
Can I ask everyone to share a little bit about their post-rebuttal feelings about the paper by replying to this message thread, and update their original review/rating of the paper accordingly at your earliest convenience? Thanks a lot in advance!
Best, your AC