A Pitch Detection Method Based on Deep Neural Network

CAO Meng; LI Hong-yan; ZHAO Rong-rong

Chinese

您当前的位置：

首页 >

文章列表页 >

A Pitch Detection Method Based on Deep Neural Network

更新时间：2026-09-04

- A Pitch Detection Method Based on Deep Neural Network
- Vol. 33, Issue 6, Pages: 143-146(2016)
- 作者机构：
  
  太原理工大学信息工程学院,山西,太原,030024
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2016
- 稿件说明：
移动端阅览
曹猛, 李鸿燕, 赵蓉蓉. 一种基于深度神经网络的基音检测算法[J]. 微电子学与计算机, 2016, 33(6): 143-146.

CAO Meng, LI Hong-yan, ZHAO Rong-rong. A Pitch Detection Method Based on Deep Neural Network[J]. 2016, 33(6): 143-146.
曹猛, 李鸿燕, 赵蓉蓉. 一种基于深度神经网络的基音检测算法[J]. 微电子学与计算机, 2016, 33(6): 143-146. DOI：

CAO Meng, LI Hong-yan, ZHAO Rong-rong. A Pitch Detection Method Based on Deep Neural Network[J]. 2016, 33(6): 143-146. DOI：

摘要

针对强噪声干扰环境下的基音检测这一挑战性问题

提出了一种基于深度神经网络的基音检测算法.该算法运用监督学习方法估计基音

在混合语音数据中得到概率性的基音状态.通过静态帧级声音特征训练

采用深度神经网络模拟每个基音状态产生的后验概率

最后执行维特比算法将基音状态连接成基音曲线.实验结果表明: 提出的基音检测算法在不同强噪声甚至混响环境中具有很强的鲁棒性

而且明显胜过其他的基音检测算法.

Abstract

Based ondeep neural network (DNN)

a pitch detection algorithm is proposed to solve the challenging problem of pitch detecting in strong noisy background.In this paper

we estimate pitch using supervised learning

where the probabilistic pitch states are directly learned from noisy speech data. The feedforward deep neural network is trained on stastic frame-level acoustic features to produce accurate probabilistic outputs of pitch states

which are then connected into pitch contours by Viterbi decoding.The experimental results show that the proposed algorithm are robust to different noise conditions and can even be applied to reverberant speech.The proposed approach outperforms other state-of-art pitch tracking algorithms.

关键词

Keywords

references

S Gonzalez, M Brookes. A pitch estimation algorithm robust to high levels of noise[J]. Audio Speech Lang. Process., 2014, 22(2): 518-530. DOI: 518

赵力. 语音信号处理[M]. 北京: 机械工程出版社, 2009: 37-43. DOI: 37

由红, 陈健. 改进的频域基音检测算法[J]. 上海交通大学学报, 2001, 35(6): 855-858. DOI: 855

王耀琦, 王小鹏. 一种低信噪比环境下的基音检测方法[J]. 铁道学报, 2012, 34(2): 58-62. DOI: 58

Geoffrey Hinton, Ruslan Salakhutdinov. Disc- overing binary codes for documents by learning deep generative models[J]. Topic in Cognitive Science, 2011, 3(1): 74-91. DOI: 74

王民, 孙洁, 贠卫国, 等. 基于两层神经网络的基音检测算法[J]. 计算机工程与应用, 2014, 50(5): 199-202. DOI: 199

Z Jin, D L Wang. A multipich tracking algo- rithm for noisy and reverberant speech[C]// proceedings of the 2010 IEEE international conference on Acous tics, Speech and Signal Processing. Dallas, TX: IEEE, 2010: 4218-4221.

胡立波, 吴月萍, 孙光中. 基于同态滤波的基音检测算法[J]. 微电子学与计算机, 2009, 26(4): 95-97. DOI: 95

潘伟深, 金连文, 冯子勇. 基于多尺度梯度及深度神经网络的汉子识别[J]. 北京航空航天大学学报, 2015, 41(4): 751-756. DOI: 751

王民, 曹绘, 要趁红. 一种改进的小波变换基音检测算法[J]. 重庆邮电大学学报(自然科学版), 2012, 24(3): 283-287. DOI: 283

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Steganography model guided by attention mechanism and improved dense convolution

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

A review of large model development: technological evolution from BERT to Deepseek

High gain stability high temperature operational amplifier based on reverse body bias

Aerial vehicle detection algorithm based on multi-scale fusion and small-object enhancement

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰