Saved in:
Bibliographic Details
Main Authors: Fang, Zihao, Shen, Yingda, Guan, Zifan, Song, Tongtong, Liu, Zhenyi, Wu, Zhizheng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.08046
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Whispered speech lacks vocal fold vibration and fundamental frequency, resulting in degraded acoustic cues and making whisper-to-normal (W2N) conversion challenging, especially with limited parallel data. We propose WhispEar, a bidirectional framework based on unified semantic representations that capture speaking-mode-invariant information shared by whispered and normal speech. The framework contains both W2N and normal-to-whisper (N2W) models. Notably, the N2W model enables zero-shot pseudo-parallel whisper generation from abundant normal speech, allowing scalable data augmentation for W2N training. Increasing generated data consistently improves performance. We also release the largest bilingual (Chinese-English) whispered-normal parallel corpus to date. Experiments demonstrate that WhispEar outperforms strong baselines and benefits significantly from scalable pseudo-parallel data.