Scribd
Upload
58 views16 pages

Internship

This document summarizes an internship project analyzing a Zomato dataset from Bengaluru, India. The internship involved data acquisition and cleaning of the dataset containing over 51,000 records on restaurants. Data visualization, modeling, and testing were performed. The goal was to understand factors affecting restaurant establishment and ratings in Bengaluru.

Uploaded by

Bhavana MU 012
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
58 views16 pages

Internship

This document summarizes an internship project analyzing a Zomato dataset from Bengaluru, India. The internship involved data acquisition and cleaning of the dataset containing over 51,000 records on restaurants. Data visualization, modeling, and testing were performed. The goal was to understand factors affecting restaurant establishment and ratings in Bengaluru.

Uploaded by

Bhavana MU 012
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Internship Seminar On

Zomato Bengaluru Dataset

Aishwarya Jyothi M P
4PM18CS023

Under the guidance of: Co-Ordinator:


Dr. Likewin Thomas
Associate Professor, CSE, PESITM, Shivamogga
Contents
1. Abstract
2. About The Comapany
3. About The Department
4. Task Performed
5. Specific Outcome
6. Contribution To The Project
7. Conclusion

1 Speech emotion recognition


Abstract

The basic idea of analyzing the Zomato dataset is to get a fair idea about the factors affecting the
establishment of different types of the restaurant at different places in Bengaluru, aggregate rating
of each restaurant, Bengaluru being one such city has more than 12,000 restaurants with
restaurants serving dishes from all over the world. With each day new restaurants opening the
industry hasn’t been saturated yet and the demand is increasing day by day. In spite of the
increasing demand, however, has become difficult for new restaurants to compete with established
restaurants. 

2 Speech emotion recognition


About The Company
• Speech Emotion Recognition (SER) is the task of recognizing the emotional aspects of speech.
• The voice based intelligent devices are gaining popularity in a wide range of applications.
• Emotion recognition systems aim to create efficient, real-time methods of detecting the emotions
of call center customers, self-driving car users and many other human-machine communication
users.
• Adding emotions to machines has been recognized as a critical factor in making machines appear
and act in a human like manner.

3 Speech emotion recognition


About The Department

XYZ

4 Speech emotion recognition


Title of the paper, Year & indexing About the papers Gap Analysis of the paper
[4] Speech Emotion Recognition This paper presents a method for Noise reduction algorithm can be
in Neurological Disorders Using speech emotion recognition using applied for model improvement in
Convolutional Neural Network deep convolutional neural network preprocessing step.
IEEE (CNN) with data agumentation
Authors: method to classify the speech
Sharif Noor Zisad, Mohammad spectrograms.
Shahadat Hossain, Karl Andersson

23 January 2020

7 Speech emotion recognition


Task Performed
•Data Acquisition And Data Cleaning
•Data Visualization
•Data Modelling
•Testing
•Comparision And Measurement

8 Speech emotion recognition


Data Acquisition And Data Cleaning

The Zomato Bengaluru dataset contains 51717 entries/records of Data and 17 columns/features
such as URL, Address, Name, Online_order, Book_table, Rating, Phone number, Location,
Restaurant type, Dish liked, Cuisines, Average cost for 2 persons, Reviews_list, Menu and more.

9 Speech emotion recognition


Data collection
There are 1044 files in this section of the RAVDESS: The RAVDESS is a group of 24
professional actors (12 women,12 men) who perform two lexically-related phrases in a neutral
North American dialect. Calm, happy, sad, furious, and frightening expressions are all included in
song emotions. Each expression has two emotional intensity levels (normal and strong),as well as
a neutral expression.

10 Speech emotion recognition


Speech Pre-Processing
 Silence Removal
The masking method is used to remove unneeded empty voice surrounding the primary audio speech by
setting the threshold value to 0.0005 in order to remove signal rates that are below the threshold value.

11 Speech emotion recognition


Feature Extraction
We are going to represent our audio in forms of 3 features:
MFCC :Mel Frequency Cepstral Coefficient, represents the short-term power spectrum of a sound.
Chroma :Represents 12 different pitch classes.
Mel :Spectrogram Frequency

12 Speech emotion recognition


CNN Model

13 Speech emotion recognition


Timeline

Name of the Event Scheduled Date

Phase 1 FINAL Seminar 09-02-2022,10-02-2022


Review Seminar March
Completion of Second Objective March-April
Progress Seminar- 2 April
Completion of Third Objective April-May
Phase 2 Seminar April-May

14 Speech emotion recognition


Summary
The goal of this project is to create a machine learning model that can recognize
emotions from the speech we exchange all of the time. Based on speech input, it can
detect several emotions such as Happy, Sad, Surprise, Disgust, and Neutral by taking
into account both acoustic and lexical data.

15 Speech emotion recognition


References
[1].Margaret Lech, Melissa Stolar, Christopher Best and Robert Bolia ,” Real-Time Speech Emotion
Recognition Using a Pre-trained Image Classification Network”,
26 May 2020.

[2]. Yixiong Pan, Peipei Shen and Liping Shen ,” Speech Emotion Recognition using Support vector
machine”,2- April-2021.

[3]. Sandra Ottl, Shahin Amiriparian, Maurice Gerczuk “Group-level Speech Emotion Recognition
Utilising Deep Spectrum Features”,25 October 2020

[4]. Sharif Noor Zisad, Mohammad Shahadat Hossain, Karl Andersson ,” Speech emotion recognition
in neurological disorders”, September 2020.

16 Speech emotion recognition


Thank You

17 Speech emotion recognition

You might also like