arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.16003eess.AS
收藏

探索纯注意力机制在盲房间参数估计中的能力

Exploring the Power of Pure Attention Mechanisms in Blind Room Parameter Estimation

Chunxi Wang, Maoshen Jia, Meiran Li, Changchun Bao, Wenyu Jin

AI总结:

本研究针对盲房间参数估计任务,提出无卷积的 Audio Spectrogram Transformer 模型,结合分块、注意力机制与预训练 Vision Transformer 跨模态迁移学习,在多种任务中显著提升性能并增强对变长输入的鲁棒性。

摘要:

声学环境的动态参数化在音频处理领域引起了广泛关注。在设计用于各种音频渲染应用的音频滤波器时,局部房间声学特性的精确表示至关重要。该背景下的关键参数包括混响时间(RT60)和房间几何体积。近年来,神经网络已被广泛应用于盲房间参数估计任务中。然而,纯注意力机制能否在该任务中取得更优性能仍是一个问题。为解决这一问题,本研究基于单耳含噪语音信号进行盲房间参数估计。研究考察了多种模型架构,包括提出的一种基于注意力的模型。该模型是无卷积的 Audio Spectrogram Transformer,利用了分块(patch splitting)、注意力机制以及来自预训练 Vision Transformer 的跨模态迁移学习。实验结果表明,所提出的基于注意力机制的模型,仅依赖注意力机制而不使用卷积,在各种房间参数估计任务中表现出显著提升的性能,尤其是在专用预训练和数据增强方案的帮助下。此外,与现有方法相比,该模型在处理可变长度音频输入时展现出更具优势的适应性和鲁棒性。

英文摘要:

Dynamic parameterization of acoustic environments has drawn widespread attention in the field of audio processing. Precise representation of local room acoustic characteristics is crucial when designing audio filters for various audio rendering applications. Key parameters in this context include reverberation time (RT60) and geometric room volume. In recent years, neural networks have been extensively applied in the task of blind room parameter estimation. However, there remains a question of whether pure attention mechanisms can achieve superior performance in this task. To address this issue, this study employs blind room parameter estimation based on monaural noisy speech signals. Various model architectures are investigated, including a proposed attention-based model. This model is a convolution-free Audio Spectrogram Transformer, utilizing patch splitting, attention mechanisms, and cross-modality transfer learning from a pretrained Vision Transformer. Experimental results suggest that the proposed attention mechanism-based model, relying purely on attention mechanisms without using convolution, exhibits significantly improved performance across various room parameter estimation tasks, especially with the help of dedicated pretraining and data augmentation schemes. Additionally, the model demonstrates more advantageous adaptability and robustness when handling variable-length audio inputs compared to existing methods.

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。

↑