الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extractors are built and evaluated for separation on synthetic mixtures, leaving listening quality and meeting behavior largely untested. We introduce Audio-Visual Personalized Voice Quality Enhancement (AV-PVQE), which approaches these requirements from the other direction. We start from a personalized speech enhancement model that reconstructs a requested voice at high quality but confuses the target in 46% of two-speaker mixtures despite clean enrollment. Adding mouth features at its speaker-conditioning input and jointly fine-tuning the visual and reconstruction networks reduces this rate to 1.6%, with no future frames and 20 ms of algorithmic delay. Compared with an online autoregressive audio-visual extractor, AV-PVQE yields separation gains on two synthetic benchmarks and larger gains on recorded meetings, and keeps its advantage on excerpts with more speakers than the fine-tuning mixtures. In personalized P.835 listening tests on two meeting corpora, it improves overall quality over this extractor by 0.57 and 0.63 MOS, with similar mean rating relative to the starting model. Preservation and rejection tests show that it keeps the target intact when no competing voice is present and suppresses competing speech when the target is absent.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Rashed, R., Filipi, S., & Cutler, R. (2026). تكييف تحسين الكلام الشخصي للاستخلاص المستهدف للمتحدث السمعي البصري منخفض التأخير. https://omanscience.com/ar/articles/adapting-personalized-speech-enhancement-for-low-latency-audio-visual-target-speaker-extraction
MLA 9
Rashed, Rayhan, et al. "تكييف تحسين الكلام الشخصي للاستخلاص المستهدف للمتحدث السمعي البصري منخفض التأخير." https://omanscience.com/ar/articles/adapting-personalized-speech-enhancement-for-low-latency-audio-visual-target-speaker-extraction.
شيكاغو (المؤلف–التاريخ)
Rashed, Rayhan, Senja Filipi, and Ross Cutler. 2026. "تكييف تحسين الكلام الشخصي للاستخلاص المستهدف للمتحدث السمعي البصري منخفض التأخير." https://omanscience.com/ar/articles/adapting-personalized-speech-enhancement-for-low-latency-audio-visual-target-speaker-extraction.
هارفارد
Rashed, R., Filipi, S. and Cutler, R. (2026) 'تكييف تحسين الكلام الشخصي للاستخلاص المستهدف للمتحدث السمعي البصري منخفض التأخير', Available at: https://omanscience.com/ar/articles/adapting-personalized-speech-enhancement-for-low-latency-audio-visual-target-speaker-extraction.
فانكوفر
Rashed R, Filipi S, Cutler R. تكييف تحسين الكلام الشخصي للاستخلاص المستهدف للمتحدث السمعي البصري منخفض التأخير. https://omanscience.com/ar/articles/adapting-personalized-speech-enhancement-for-low-latency-audio-visual-target-speaker-extraction
IEEE
R. Rashed, S. Filipi, and R. Cutler, "تكييف تحسين الكلام الشخصي للاستخلاص المستهدف للمتحدث السمعي البصري منخفض التأخير," https://omanscience.com/ar/articles/adapting-personalized-speech-enhancement-for-low-latency-audio-visual-target-speaker-extraction.