paper-with-me

홈 › Papers

Latent Filling: Latent Space Data Augmentation for Zero-shot Speech Synthesis

2023-10-05 · Jae-Sung Bae, Joun Yeop Lee, Ji-Hyun Lee, Seongkyu Mun, Taehwa Kang, Hoon-Young Cho, Chanwoo Kim

Previous works in zero-shot text-to-speech (ZS-TTS) have attempted to enhance its systems by enlarging the training data through crowd-sourcing or augmenting existing speech data. However, the use of low-quality data has led to a decline in the overall system performance. To avoid such degradation, instead of directly augmenting the input data, we propose a latent filling (LF) method that adopts simple but effective latent space data augmentation in the speaker embedding space of the ZS-TTS system. By incorporating a consistency loss, LF can be seamlessly integrated into existing ZS-TTS systems without the need for additional training stages. Experimental results show that LF significantly improves speaker similarity while preserving speech quality.

📄 PDF Abstract BibTeX arXiv:2310.03538

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationSpeech Synthesistext-to-speechText to Speech

Similar Papers 제목 키워드 기반

Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization

2024-10-27 · Mohammad Hassan Vali, Tom Bäckström

Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable …

Data AugmentationQuantization

Towards Composable Distributions of Latent Space Augmentations

2023-03-06 · Omead Pooladzandi, Jeffrey Jiang, Sunay Bhat, Gregory Pottie

We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performan…

Image Augmentationimage-classificationImage Classification

Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Exploration

2023-02-05 · Onur Boyar, Ichiro Takeuchi

Latent Space Bayesian Optimization (LSBO) combines generative models, typically Variational Autoencoders (VAE), with Bayesian Optimization (BO) to generate de-novo objects of interest. However, LSBO faces challenges due …

Bayesian OptimizationData AugmentationImage Generation

Generative De-Quantization for Neural Speech Codec via Latent Diffusion

2023-11-14 · Haici Yang, Inseon Jang, Minje Kim

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity incre…

DecoderQuantizationRepresentation Learning

Dual-Space Augmented Intrinsic-LoRA for Wind Turbine Segmentation

2024-12-30 · Shubh Singhal, Raül Pérez-Gonzalo, Andreas Espersen, Antonio Agudo

Accurate segmentation of wind turbine blade (WTB) images is critical for effective assessments, as it directly influences the performance of automated damage detection systems. Despite advancements in large universal vis…

Image SegmentationSegmentationSemantic Segmentation