REVIEW 7 cited by
Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of integrating subjective human evaluation into the TTS training loop. Inspired by the recent success of reinforcement learning from human feedback, we propose a comprehensive sampling-annotating-learning framework tailored to TTS optimization, namely uncertainty-aware optimization (UNO). Specifically, UNO eliminates the need for a reward model or preference data by directly maximizing the utility of speech generations while considering the uncertainty that lies in the inherent variability in subjective human speech perception and evaluations. Experimental results of both subjective and objective evaluations demonstrate that UNO considerably improves the zero-shot performance of TTS models in terms of MOS, word error rate, and speaker similarity. Additionally, we present a remarkable ability of UNO that it can adapt to the desired speaking style in emotional TTS seamlessly and flexibly.
Forward citations
Cited by 7 Pith papers
-
MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
MPO improves TTS alignment by constructing multi-dimensional preference pairs and adding cross-entropy regularization to DPO, yielding better intelligibility, speaker similarity, and prosody.
-
TTS-1 Technical Report
A new TTS system family combines pre-training, supervised fine-tuning, and GRPO reinforcement learning with a 48 kHz codec to produce multilingual speech with in-context voice cloning.
-
DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis
Reinforcement learning on duration prediction improves intelligibility and speaker similarity in a 4-step distilled text-to-speech model, and teacher-guided sampling recovers prosodic diversity.
-
Differentiable Reward Optimization for LLM based TTS system
DiffRO optimizes codec-based TTS models directly on differentiable token-level rewards, improving WER and enabling zero-shot emotion control.
-
Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy
DCAR dynamically schedules chunk-wise token prediction in AR TTS, improving WER by up to 72.27% relative and speeding up inference by up to 2.89x over next-token baselines.
-
VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation
VoiceStar uses a progress-based rotary position embedding and mixed prompt training to give zero-shot voice cloning precise duration control and much longer output than training clips.
-
Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation
PER-based preference optimization (DPO, PPO, GRPO) reduces lyric-to-song hallucination in an audio language model, with the largest gains from DPO plus reject sampling.
Discussion (0). Sign in to comment.