paper-with-me

홈 › Papers

MicAugment: One-shot Microphone Style Transfer

2020-10-19 · Zalán Borsos, Yunpeng Li, Beat Gfeller, Marco Tagliasacchi

A crucial aspect for the successful deployment of audio-based models "in-the-wild" is the robustness to the transformations introduced by heterogeneous acquisition conditions. In this work, we propose a method to perform one-shot microphone style transfer. Given only a few seconds of audio recorded by a target device, MicAugment identifies the transformations associated to the input acquisition pipeline and uses the learned transformations to synthesize audio as if it were recorded under the same conditions as the target audio. We show that our method can successfully apply the style transfer to real audio and that it significantly increases model robustness when used as data augmentation in the downstream tasks.

📄 PDF Abstract BibTeX arXiv:2010.09658

Code (5)

MindSpore-scientific-2/code-4/tree/main/MicAugment mindspore
MindSpore-scientific/code-1/tree/main/MicAugment mindspore
MindSpore-scientific/code-11/tree/main/MicAugment mindspore
akashrajkn/micaugment pytorch
pwc-1/Paper-9/tree/main/7/MicAugment mindspore

Tasks

Data AugmentationStyle Transfer

Similar Papers 제목 키워드 기반

TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings

2024-06-21 · Zachary Horvitz, Ajay Patel, Kanishk Singh, Chris Callison-Burch 외

The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-sh…

AttributeLanguage ModelingLanguage ModellingSmall Language Model+3

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

2023-04-24 · CVPR 2023 1 · Hao Tang, Songhua Liu, Tianwei Lin, Shaoli Huang 외

Transformer-based models achieve favorable performance in artistic style transfer recently thanks to its global receptive field and powerful multi-head/layer attention operations. Nevertheless, the over-paramerized multi…

Meta-LearningStyle Transfer

A Recipe For Arbitrary Text Style Transfer with Large Language Models

2021-09-08 · ACL 2022 5 · Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen 외

In this paper, we leverage large language models (LMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewritin…

SentenceSentence ReWritingStyle TransferText Style Transfer+1

A Recipe For Arbitrary Text Style Transfer with Large Language Models

2021-06-16 · ACL ARR October 2021 10 · Anonymous

In this paper, we leverage large language models (LLMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewriti…

SentenceSentence ReWritingStyle TransferText Style Transfer+1

TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control

2024-09-24 · Yu Zhang, Ziyue Jiang, RuiQi Li, Changhao Pan 외

Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles (including singing method, emotion, rhythm, technique, and pronunc…

ClusteringLanguage ModellingQuantizationRhythm+2