SDAILGASSep 19, 2024

DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency

arXiv:2409.12992v13 citationsh-index: 10
Originality Incremental advance
AI Analysis

This addresses speech editing challenges for users needing unrestricted text modifications, but it is incremental as it builds on existing techniques with specific enhancements.

The paper tackles the problem of maintaining intelligibility and acoustic consistency in text-based speech editing for out-of-domain text, achieving state-of-the-art performance in both in-domain and out-of-domain scenarios.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes