arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.01709cs.SDcs.CLcs.LGeess.AS
收藏

嵌入式系统中小占用空间的文本无关说话人确认

Small footprint Text-Independent Speaker Verification for Embedded Systems

Sonos Inc.(Sonos公司)

Julien Balian, Raffaele Tavarone, Mathieu Poumeyrol, Alice Coucke

摘要:

说话人验证的深度神经网络方法已被证明是成功的,但最先进的(SOTA)系统的典型计算要求使其不适合嵌入式应用。在这项工作中,我们提出了一个两阶段的模型架构的数量级小于常见的解决方案(237.5K的学习参数,11.5MFLOPS),达到了3.31%的竞争力的结果,平等的出错率(EER),以及建立VoxCeleb1验证测试集。我们展示了在物联网系统的典型小型设备上运行我们的解决方案的可能性,例如Raspberry Pi 3B,在5s长的话语上的延迟小于200ms。此外,我们评估我们的模型在声学上具有挑战性的VOiCES语料库。我们报告说,相对于2019年VOiCES远程挑战赛的最佳评分模型,EER仅增加了2.6个百分点,而学习参数的数量减少了25.6倍。

英文摘要:

Deep neural network approaches to speaker verification have proven successful, but typical computational requirements of State-Of-The-Art (SOTA) systems make them unsuited for embedded applications. In this work, we present a two-stage model architecture orders of magnitude smaller than common solutions (237.5K learning parameters, 11.5MFLOPS) reaching a competitive result of 3.31% Equal Error Rate (EER) on the well established VoxCeleb1 verification test set. We demonstrate the possibility of running our solution on small devices typical of IoT systems such as the Raspberry Pi 3B with a latency smaller than 200ms on a 5s long utterance. Additionally, we evaluate our model on the acoustically challenging VOiCES corpus. We report a limited increase in EER of 2.6 percentage points with respect to the best scoring model of the 2019 VOiCES from a Distance Challenge, against a reduction of 25.6 times in the number of learning parameters.

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。

↑