SMALL-FOOTPRINT KEYWORD SPOTTING USING DEEP NEURAL NETWORKS学习摘要

该博客介绍了基于深度神经网络(DNN)的关键词检测方法——Deep KWS System,与传统HMM方法相比,它能更快地反馈,减少运算次数和空间占用。DNN直接预测关键词或子词单元,后处理模块产生最终置信度。实验结果显示,Deep KWS在性能和效率上优于基线HMM模型。
摘要由CSDN通过智能技术生成

由于个人能力有限,所有理解可能有误,所以有什么问题,可以直接评论告诉我,我会及时更改,谢谢。非全文翻译,只是找了比较重要的地方翻译并加上了自己的理解。

论文来源:
这里写图片描述
在此致谢。

基于DNN的语音唤醒方法DEEP KWS SYSTEM,每10ms反馈一次,相比于原始的HMM方法,减少了反应时间,不用收录入所有的语音再做反应,也不用有decoding过程,减少了运算次数,减少了空间占用。

ABSTRACT
A deep neural network is trained to directly predict the keyword(s) or subword units of the keyword(s) followed by a posterior handling method producing a final confidence score.

  1. INTRODUCTION
    Keyword Spotting (KWS) aims at detecting predefined keywords in an audio stream. In this generative approach, an HMM model is trained for each keyword, and a filler(不需要的词) model HMM is trained from the non-keyword segments of the speech signal (fillers).We propose a simple discriminative KWS approach based on deep neural networks that is appropriate for mobile devices. We refer to it as Deep KWS . A deep neural network is trained to directly predict the keyword(s) or subword units of the keyword(s) followed by a posterior handling method producing a final confidence score.
  2. DEEP KWS SYSTEM
    The framework consists of three major components: (i) a feature extraction module, (ii) a deep neural network, and (iii) a posterior handling module. The feature extraction module (i) performs voice-activity detection and generates a vector of features e
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值