Deep AHS:一种用于声学啸叫抑制的深度学习方法
Deep AHS: A Deep Learning Approach to Acoustic Howling Suppression
AI总结:
该研究将声学啸叫抑制建模为监督学习任务,提出基于注意力 RNN 和教师强制训练的 Deep AHS,可在实时流式场景中无需检测即可从根本上抑制啸叫。
摘要:
本文将声学啸叫抑制(AHS)表述为一个监督学习问题,并提出一种称为 Deep AHS 的深度学习方法来解决该问题。Deep AHS 采用教师强制方式进行训练,将循环的啸叫抑制过程转化为瞬时语音分离过程,以简化问题并加速模型训练。所提方法利用经过适当设计的特征,并训练一个基于注意力的循环神经网络(RNN),从麦克风录音中提取目标信号,从而衰减可能导致啸叫的回放信号。本文研究了不同的训练策略,并实现了一种以循环模式运行的流式推理方法,用于评估所提方法在实时啸叫抑制方面的性能。Deep AHS 无需啸叫检测,并从本质上阻止啸叫发生,从而为音频系统设计带来更大灵活性。实验结果表明,所提方法在不同场景下均能有效实现啸叫抑制。
英文摘要:
In this paper, we formulate acoustic howling suppression (AHS) as a supervised learning problem and propose a deep learning approach, called Deep AHS, to address it. Deep AHS is trained in a teacher forcing way which converts the recurrent howling suppression process into an instantaneous speech separation process to simplify the problem and accelerate the model training. The proposed method utilizes properly designed features and trains an attention based recurrent neural network (RNN) to extract the target signal from the microphone recording, thus attenuating the playback signal that may lead to howling. Different training strategies are investigated and a streaming inference method implemented in a recurrent mode used to evaluate the performance of the proposed method for real-time howling suppression. Deep AHS avoids howling detection and intrinsically prohibits howling from happening, allowing for more flexibility in the design of audio systems. Experimental results show the effectiveness of the proposed method for howling suppression under different scenarios.
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。