arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07244eess.AScs.LGcs.SDstat.ML
收藏

基于移动音频流网络的高效低延迟语音增强

Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networks

Samsung R\&D Institute Poland

Michał Romaniuk, Piotr Masztalski, Karol Piaskowski, Mateusz Matuszewski

摘要:

我们提出了移动音频流网络(MASnet)的有效的低延迟语音增强,这是特别适合于移动设备和其他应用程序的计算能力是一个限制。MASnet处理线性尺度频谱图,将连续的噪声帧转换为复值比率掩模,然后将其应用于相应的噪声帧。MASnet可以在低延迟增量推理模式下运行,该模式与逐层批处理模式的复杂性相匹配。与类似的全卷积架构相比,MASnet结合了去卷积和逐点卷积,大大减少了每秒融合乘法累加运算(FMA/s),但代价是SNR有所降低。

英文摘要:

We propose Mobile Audio Streaming Networks (MASnet) for efficient low-latency speech enhancement, which is particularly suitable for mobile devices and other applications where computational capacity is a limitation. MASnet processes linear-scale spectrograms, transforming successive noisy frames into complex-valued ratio masks which are then applied to the respective noisy frames. MASnet can operate in a low-latency incremental inference mode which matches the complexity of layer-by-layer batch mode. Compared to a similar fully-convolutional architecture, MASnet incorporates depthwise and pointwise convolutions for a large reduction in fused multiply-accumulate operations per second (FMA/s), at the cost of some reduction in SNR.

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。

↑