WhispSynth: Scaling Multilingual Whisper Corpus through Real Data Curation and A Novel Pitch-free Generative Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Tianyi, Ye, Jiaxin, Zhang, Yuanming, Le, Xiaohuai, Xia, Xianjun, Huang, Chuanzeng, Lu, Jing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917345498234880
author Tan, Tianyi
Ye, Jiaxin
Zhang, Yuanming
Le, Xiaohuai
Xia, Xianjun
Huang, Chuanzeng
Lu, Jing
author_facet Tan, Tianyi
Ye, Jiaxin
Zhang, Yuanming
Le, Xiaohuai
Xia, Xianjun
Huang, Chuanzeng
Lu, Jing
contents Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper, we introduce WhispSynth, a large-scale multilingual corpus constructed via a novel high-fidelity generative framework. Specifically, we propose a pipeline integrating Differentiable Digital Signal Processing (DDSP)-based pitch-free method with Text-to-Speech (TTS) models. This framework refines a comprehensive collection of resources, including our newly constructed WhispNJU dataset, into 118 hours of high-fidelity whispered speech from 479 speakers. Unlike standard synthetic or noisy real data, our data engine faithfully preserves source vocal timbre and linguistic content while ensuring acoustic consistency, providing a robust foundation for text-to-whisper research. Experimental results demonstrate that WhispSynth exhibits significantly higher quality than existing corpora. Moreover, our CosyWhisper, tuned with WhispSynth, achieves speech naturalness on par with ground-truth samples. The official implementation and related resources are available at https://github.com/tan90xx/cosywhisper.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14853
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WhispSynth: Scaling Multilingual Whisper Corpus through Real Data Curation and A Novel Pitch-free Generative Framework
Tan, Tianyi
Ye, Jiaxin
Zhang, Yuanming
Le, Xiaohuai
Xia, Xianjun
Huang, Chuanzeng
Lu, Jing
Sound
Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper, we introduce WhispSynth, a large-scale multilingual corpus constructed via a novel high-fidelity generative framework. Specifically, we propose a pipeline integrating Differentiable Digital Signal Processing (DDSP)-based pitch-free method with Text-to-Speech (TTS) models. This framework refines a comprehensive collection of resources, including our newly constructed WhispNJU dataset, into 118 hours of high-fidelity whispered speech from 479 speakers. Unlike standard synthetic or noisy real data, our data engine faithfully preserves source vocal timbre and linguistic content while ensuring acoustic consistency, providing a robust foundation for text-to-whisper research. Experimental results demonstrate that WhispSynth exhibits significantly higher quality than existing corpora. Moreover, our CosyWhisper, tuned with WhispSynth, achieves speech naturalness on par with ground-truth samples. The official implementation and related resources are available at https://github.com/tan90xx/cosywhisper.
title WhispSynth: Scaling Multilingual Whisper Corpus through Real Data Curation and A Novel Pitch-free Generative Framework
topic Sound
url https://arxiv.org/abs/2603.14853