Geneses: Unified Generative Speech Enhancement and Separation

2026-01-26

AI Summary

Real-world recordings are often degraded by overlapping speech from multiple speakers and complex non-additive distortions, which pose significant challenges for conventional speech enhancement and separation methods. To address this issue, this work proposes Geneses, a novel framework that, for the first time, integrates latent flow matching with a multimodal diffusion Transformer to enable end-to-end joint speech enhancement and separation using self-supervised representations. Evaluated on the LibriTTS-R dataset, the proposed method substantially outperforms traditional masking-based approaches across multiple objective metrics and demonstrates strong robustness under diverse and challenging degradation conditions.

Technology Category

• Machine Learning: Multimodal Learning
• Natural Language Processing: Generation
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Privacy-enhancing technologies

Abstract

Real-world audio recordings often contain multiple speakers and various degradations, which limit both the quantity and quality of speech data available for building state-of-the-art speech processing models. Although end-to-end approaches that concatenate speech enhancement (SE) and speech separation (SS) to obtain a clean speech signal for each speaker are promising, conventional SE-SS methods suffer from complex degradations beyond additive noise. To this end, we propose \textbf{Geneses}, a generative framework to achieve unified, high-quality SE--SS. Our Geneses leverages latent flow matching to estimate each speaker's clean speech features using multi-modal diffusion Transformer conditioned on self-supervised learning representation from noisy mixture. We conduct experimental evaluation using two-speaker mixtures from LibriTTS-R under two conditions: additive-noise-only and complex degradations. The results demonstrate that Geneses significantly outperforms a conventional mask-based SE--SS method across various objective metrics with high robustness against complex degradations. Audio samples are available in our demo page.

Problem

• speech enhancement
• speech separation
• complex degradations
• multi-speaker mixtures
• real-world audio

Innovation

• generative speech enhancement
• speech separation
• latent flow matching
• diffusion Transformer
• self-supervised learning