ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis
We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning. To address this issue, we propose ZeSTA, a simple domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling to stabilize adaptation under extremely limited target data, without modifying the base architecture. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality. Audio samples are available on our web page.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSpeech SynthesisSimilar Papers 제목 키워드 기반
Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis
Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Introduction (NPI). This limitation hinders the deployment of robust su…
Representation LearningData AugmentationDomain AdaptationSchema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking
Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains unseen at training time. Current large l…
Data AugmentationDialogue State TrackingDomain AdaptationLanguage Modeling+3MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation
Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of-art performance across tasks in text processing. Data Augmentation techniques have also helped b…
Data AugmentationLanguage ModelingLanguage ModellingMachine Translation+2Generate then Refine: Data Augmentation for Zero-shot Intent Detection
In this short paper we propose a data augmentation method for intent detection in zero-resource domains. Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive i…
Data AugmentationDiversityIntent DetectionLanguage Modeling+2Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types
Event Argument Extraction (EAE) is an extremely difficult information extraction problem -- with significant limitations in few-shot cross-domain (FSCD) settings. A common solution to FSCD modeling is data augmentation. …
Data AugmentationEvent Argument Extraction