CORTEXA
← Browse
arxivcs.SDcs.AI2026-07-01

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

Zuda Yu, Qianhui Xu, Ting Chen, Junhui Zhang, Tao Fu, Hongjiang Yu, Qiangqing Wang, Yang Song

Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we propose a unified guidance framework that enhances generation efficiency and robustness through two complementary strategies. On the data front, we introduce Data-guidance via heterogeneous augmentation, encouraging the model to disentangle linguistic content from acoustic residue. In parallel, we propose an enhanced Model-guidance mechanism that synergizes trajectory rectification with a novel intrinsic guidance objective. This approach distills conditional knowledge into network weights and straightens inference trajectory path, thereby eliminating Classifier-Free Guidance (CFG) overhead. Experiments demonstrate that our framework accelerates inference by nearly three times while effectively improving speaker similarity compared to state-of-the-art baselines.

View free PDFSource page

Related papers

arxivcs.SDcs.AI2026-07-17

AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis

Zhenqi Jia, Yuan Zhao, Aruukhan, Rui Liu, Haizhou Li

Conversational Speech Synthesis (CSS) aims to synthesize speech with human-like emotional expression and contextual consistency in user-agent interactions. Existing CSS methods struggle to render authentic human emotions due to limited predefined emotion label spaces (e.g., seven…

View free PDFSource page
arxivcs.SDcs.AIeess.AS2026-07-22

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

Junyu Dai, Xinyue Fan, Weiqin Li, Xiangang Li, Yunjia Li, Bin Ma, et al.

In this report, we present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes. The proposed framework supports three tasks: Lyrics-to-Song Generation, which generates complete songs from t…

View free PDFSource page
arxivcs.SDcs.AIcs.CLeess.AS2026-06-30

UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling

Chuanbo Zhu, Wuyou Zhou, Rongxiu Zhong, Shilei Zhang, Kun Qian, Yike Guo, et al.

Speech editing aims to modify specific portions of an utterance while preserving the remaining speech. Existing approaches primarily focus on word-level content modification and typically treat content, speaker, and emotion editing as separate tasks, limiting both editing granula…

View free PDFSource page
arxiveess.AScs.AIcs.LGcs.SD2026-06-30

Improving multichannel speech enhancement through accurate room-acoustic simulations

Georg Götz, Alessia Milo, Steinar Guðjónsson, Daniel Gert Nielsen, Jesper Pedersen, Finnur Pind

Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement. While most pipelines rely on simplified geometrical acoustics, wave-based approaches offer greater physical accuracy. In this work, we examine how simulation fidelity af…

View free PDFSource page
arxivcs.SDcs.AI2026-06-28

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation

Qinzhe Hu, Chenda Li, Wangyou Zhang, Shujie Liu, Yan Lu, Yanmin Qian

Recent advances in speech separation (SS) have led to compact front-end models with small parameter sizes, yet their high computational cost remains a major barrier for deployment on edge devices. To address this, we propose TF-MoE, a sparse Mixture-of-Experts (MoE) framework tha…

View free PDFSource page
arxivcs.SDcs.AI2026-07-20

Time-Frequency Consistency Learning for Robust Speech Deepfake Detection

Jun Xue, Zhuolin Yi, Yanzhen Ren, Yihuan Huang, Jiayu Xiong, Yi Chai, et al.

Recently, speech deepfake detection (SDD) has achieved significant progress. However, its robustness evaluation remains largely confined to controlled additive noise scenarios, lacking systematic investigation of the complex distortions introduced by acoustic front-end (AFE) proc…

View free PDFSource page