基于ResNet的声纹识别

Program人工智能 |    Course Attributes |    Number of Views349Times |    Course Duration6Hours
Task0a      Assignments0a      Notes0Bar      Student Count0People
Start Learning View Course Details

Introduction
在本次实验中我们将使用 Pytorch框架来搭建一个声纹识别模型,并利用这一模型判断某段语音是否为指定的说话人所说。该实验使用语谱图信息或MFCC(梅尔倒谱系数特征)作为前端特征。使用ResNet残差神经网络作为后端分类器。对语音特征进行分类筛选。

Course Comments

   
A total of 0 comments

Sorry, there is currently no course announcement

A total of 0 notes
Supervisor
administrator
Instructors

Sorry, there is currently no teaching team