arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04859cs.SDeess.AS
收藏

Flow-TSVAD:基于潜在流匹配的目标说话人语音活动检测

Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching

Shanghai Jiao Tong University(上海交通大学);Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));National University of Singapore(新加坡国立大学)

Zhengyang Chen, Bing Han, Shuai Wang, Yidi Jiang, Yanmin Qian

AI总结:

本文首次将流匹配生成方法引入说话人日志,通过映射到潜在空间提出Flow-TSVAD,优于Seq2Seq-TSVAD,且两步推理即可收敛,多次采样集成可提升性能。

摘要:

说话人日志通常被视为一个判别性任务,使用判别性方法产生固定的日志结果。本文首次探索了基于神经网络的生成方法用于说话人日志。我们在序列到序列的目标说话人语音活动检测(Seq2Seq-TSVAD)日志系统中实现了一种基于流匹配(FM)的生成算法。实验表明,直接将生成方法应用于TS-VAD输出的原始二元标签序列空间是无效的。为解决此问题,我们提出在应用生成算法之前将二元标签序列映射到密集的潜在空间,我们提出的Flow-TSVAD方法优于Seq2Seq-TSVAD系统。此外,我们观察到FM算法在推理阶段收敛迅速,仅需两步推理即可获得有希望的结果。作为生成模型,Flow-TSVAD允许通过多次运行模型来采样不同的日志结果。此外,对多次采样实例的结果进行集成进一步提升了日志性能。

英文摘要:

Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm and our proposed Flow-TSVAD method outperforms the Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, requiring only two inference steps to achieve promising results. As a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times. Moreover, ensembling results from various sampling instances further enhances diarization performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑