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 2005.08184cs.SDeess.AS
收藏

结合DNN和GMM模型的语音激活检测方案

Voice Activity Detection Scheme by Combining DNN Model with GMM Model

Haier Smart Home Co., Ltd.(海尔智家股份有限公司)

Lu Ma, Xiaomeng Zhang, Pei Zhao, Tengrong Su

摘要:

由于深度神经网络(DNN)具有优越的建模能力,被广泛应用于语音活动检测(VAD)。然而,如果没有足够的数据,特别是实际数据可以用于训练,性能可能会下降,从而导致对环境的适应能力差。此外,大模型结构并不总是能在实际中使用,特别是对于使用受限硬件的低成本设备。而高斯混合模型(GMM)则相反,GMM模型参数可以实时更新,但建模能力较低。本文提出了将这两种模型进行深度集成的方案,以提高模型的适应性和建模能力。这是通过直接组合模型的结果并将其与DNN模型的结果一起反馈以更新GMM模型来完成的。此外,本文还设计了一种控制方案来检测语音端点。通过实验验证了该方法的优越性能,从而体现了有监督学习和无监督学习相结合的优势。

英文摘要:

Due to the superior modeling ability of deep neural network (DNN), it is widely used in voice activity detection (VAD). However, the performance may degrade if no sufficient data especially for practical data could be used for training, thus, leading to inferior ability of adaption to environment. Moreover, large model structure could not always be used in practical, especially for low cost devices where restricted hardware is used. This is on the contrary for Gaussian mixture model (GMM) where model parameters can be updated in real-time, but, with low modeling ability. In this paper, deeply integrated scheme combining these two models are proposed to improve adaptability and modeling ability. This is done by directly combining the results of models and feeding it back, together with the result of the DNN model, to update the GMM model. Besides, a control scheme is elaborately designed to detect the endpoints of speech. The superior performance by employing this scheme is validated through experiments in practical, which give an insight into the advantage of combining supervised learning and unsupervised learning.

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。

↑