Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis

• URL: http://arxiv.org/abs/2404.19622v1
• Date: Tue, 30 Apr 2024 15:22:19 GMT
• Title: Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis
• Authors: Shivam Mehta, Anna Deichler, Jim O'Regan, Birger Moëll, Jonas Beskow, Gustav Eje Henter, Simon Alexanderson,
• Abstract summary: Methods for joint and unified synthesis of speech audio and co-speech 3D gesture motion from text are a new and emerging field. Existing methods are trained on parallel data from all constituent modalities. Inspired by student-teacher methods, we propose a straightforward solution to the data shortage, by simply synthesising additional training material.
• Score: 21.210982054134686
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although humans engaged in face-to-face conversation simultaneously communicate both verbally and non-verbally, methods for joint and unified synthesis of speech audio and co-speech 3D gesture motion from text are a new and emerging field. These technologies hold great promise for more human-like, efficient, expressive, and robust synthetic communication, but are currently held back by the lack of suitably large datasets, as existing methods are trained on parallel data from all constituent modalities. Inspired by student-teacher methods, we propose a straightforward solution to the data shortage, by simply synthesising additional training material. Specifically, we use unimodal synthesis models trained on large datasets to create multimodal (but synthetic) parallel training data, and then pre-train a joint synthesis model on that material. In addition, we propose a new synthesis architecture that adds better and more controllable prosody modelling to the state-of-the-art method in the field. Our results confirm that pre-training on large amounts of synthetic data improves the quality of both the speech and the motion synthesised by the multimodal model, with the proposed architecture yielding further benefits when pre-trained on the synthetic data. See https://shivammehta25.github.io/MAGI/ for example output.

Related papers

• ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis [80.34000499166648]
  We propose a Graph-based Sampling strategy to sample more relevant tool combinations, and a Planned-generation strategy to create plans that guide the synthesis of coherent dialogues. We apply SFT on LLaMA-3.1-8B using 8,000 synthetic dialogues generated with ToolFlow. Results show that the model achieves tool-calling performance comparable to or even surpassing GPT-4, while maintaining strong general capabilities.
  arXiv  Detail & Related papers  (2024-10-24T05:45:04Z)
• Synthetic continued pretraining [29.6872772403251]
  We propose synthetic continued pretraining on a small corpus of domain-specific documents. We instantiate this proposal with EntiGraph, a synthetic data augmentation algorithm. We show how synthetic data augmentation can "rearrange" knowledge to enable more data-efficient learning.
  arXiv  Detail & Related papers  (2024-09-11T17:21:59Z)
• Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models [69.76066070227452]
  *Data Synthesis* is a promising way to train a small model with very little labeled data. We propose *Synthesis Step by Step* (**S3**), a data synthesis framework that shrinks this distribution gap. Our approach improves the performance of a small model by reducing the gap between the synthetic dataset and the real data.
  arXiv  Detail & Related papers  (2023-10-20T17:14:25Z)
• Image Captions are Natural Prompts for Text-to-Image Models [70.30915140413383]
  We analyze the relationship between the training effect of synthetic data and the synthetic data distribution induced by prompts. We propose a simple yet effective method that prompts text-to-image generative models to synthesize more informative and diverse training data. Our method significantly improves the performance of models trained on synthetic training data.
  arXiv  Detail & Related papers  (2023-07-17T14:38:11Z)
• ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning [102.46382882098847]
  We first investigate the effects of synthetic data in synthetic-to-real novel view synthesis. We propose to introduce geometry-aware contrastive learning to learn multi-view consistent features with geometric constraints. Our method can render images with higher quality and better fine-grained details, outperforming existing generalizable novel view synthesis methods in terms of PSNR, SSIM, and LPIPS.
  arXiv  Detail & Related papers  (2023-03-20T12:06:14Z)
• Synthetic Pre-Training Tasks for Neural Machine Translation [16.6378815054841]
  Our goal is to understand the factors that contribute to the effectiveness of pre-training models when using synthetic resources. We propose several novel approaches to pre-training translation models that involve different levels of lexical and structural knowledge. Our experiments on multiple language pairs reveal that pre-training benefits can be realized even with high levels of obfuscation or purely synthetic parallel data.
  arXiv  Detail & Related papers  (2022-12-19T21:34:00Z)
• FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning [58.47265392465442]
  Retrosynthetic planning aims to devise a complete multi-step synthetic route from starting materials to a target molecule. Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms. We propose a novel framework that utilizes context information for improved retrosynthetic planning.
  arXiv  Detail & Related papers  (2022-09-30T08:44:58Z)
• Advancing Semi-Supervised Learning for Automatic Post-Editing: Data-Synthesis by Mask-Infilling with Erroneous Terms [5.366354612549173]
  We focus on data-synthesis methods to create high-quality synthetic data. We present a data-synthesis method by which the resulting synthetic data mimic the translation errors found in actual data. Experimental results show that using the synthetic data created by our approach results in significantly better APE performance than other synthetic data created by existing methods.
  arXiv  Detail & Related papers  (2022-04-08T07:48:57Z)
• Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition [18.924716098922683]
  Machine learning with synthetic data is not trivial due to the gap between the synthetic and the real data distributions. We propose two novel techniques during training to mitigate the problems due to the distribution gap. We show that these methods significantly improve the training of speech recognition models using synthetic data.
  arXiv  Detail & Related papers  (2021-10-21T21:11:42Z)
• Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks [58.0240970093372]
  This paper presents a new framework for human body part segmentation based on Deep Convolutional Neural Networks trained using only synthetic data. The proposed approach achieves cutting-edge results without the need of training the models with real annotated data of human body parts.
  arXiv  Detail & Related papers  (2021-02-02T12:26:50Z)
• Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement [31.33429812278942]
  The proposed end-to-end speech synthesis model uses both speaker embedding and noise representation as conditional inputs to model speaker and noise information respectively. Experimental results show that the speech generated by the proposed approach has better subjective evaluation results than the method directly fine-tuning multi-speaker speech synthesis model.
  arXiv  Detail & Related papers  (2020-05-26T06:14:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.