DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yang, Jia, Yuhang, Zhao, Shiwan, Jiang, Ziyue, Li, Haoran, Kang, Jiarong, Qin, Yong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910613649752064
author Chen, Yang
Jia, Yuhang
Zhao, Shiwan
Jiang, Ziyue
Li, Haoran
Kang, Jiarong
Qin, Yong
author_facet Chen, Yang
Jia, Yuhang
Zhao, Shiwan
Jiang, Ziyue
Li, Haoran
Kang, Jiarong
Qin, Yong
contents As text-based speech editing becomes increasingly prevalent, the demand for unrestricted free-text editing continues to grow. However, existing speech editing techniques encounter significant challenges, particularly in maintaining intelligibility and acoustic consistency when dealing with out-of-domain (OOD) text. In this paper, we introduce, DiffEditor, a novel speech editing model designed to enhance performance in OOD text scenarios through semantic enrichment and acoustic consistency. To improve the intelligibility of the edited speech, we enrich the semantic information of phoneme embeddings by integrating word embeddings extracted from a pretrained language model. Furthermore, we emphasize that interframe smoothing properties are critical for modeling acoustic consistency, and thus we propose a first-order loss function to promote smoother transitions at editing boundaries and enhance the overall fluency of the edited speech. Experimental results demonstrate that our model achieves state-of-the-art performance in both in-domain and OOD text scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12992
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
Chen, Yang
Jia, Yuhang
Zhao, Shiwan
Jiang, Ziyue
Li, Haoran
Kang, Jiarong
Qin, Yong
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
As text-based speech editing becomes increasingly prevalent, the demand for unrestricted free-text editing continues to grow. However, existing speech editing techniques encounter significant challenges, particularly in maintaining intelligibility and acoustic consistency when dealing with out-of-domain (OOD) text. In this paper, we introduce, DiffEditor, a novel speech editing model designed to enhance performance in OOD text scenarios through semantic enrichment and acoustic consistency. To improve the intelligibility of the edited speech, we enrich the semantic information of phoneme embeddings by integrating word embeddings extracted from a pretrained language model. Furthermore, we emphasize that interframe smoothing properties are critical for modeling acoustic consistency, and thus we propose a first-order loss function to promote smoother transitions at editing boundaries and enhance the overall fluency of the edited speech. Experimental results demonstrate that our model achieves state-of-the-art performance in both in-domain and OOD text scenarios.
title DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2409.12992