vijaypurohit / speech-processing-yesno-detection Goto Github PK

Speech Processing CS 566

Assignment 01 (YES NO Detection)

Roll No: 214101058 MTech CSE'23 IITG | Vijay Purohit

Input:

• Yes/No voice data in text format using CoolEdit2000 Software
• Sample data has been clipped into 8 parts, Yes (4 parts), No (4 parts).
• present in data_input folder.

Output:

• to classify whether voice data in question is Yes or No.
  • file_name_final_values - contain output result of analysis.>Speech Processing CS 566
  • file_name_normalised - contain normalised input
  • file_name_features_extract - contain energy, zcr of frames
  • file_name_segregated_sound - contain segregated voice data.
  • present in data input folder.

1. What you have done?

   • I have presented an overview of steps in logic.txt file and followed the steps shown.

2. Instructions to execute code.

   • To execute it.
   • Just open project and run it.
   • Enter file name. (Input data and Output data is present in data_input folder.)
   • (no_sample_1.txt, no_sample_2.txt, no_sample_3.txt, no_sample_4.txt,
   • yes_sample_1.txt, yes_sample_2.txt, yes_sample_3.txt, yes_sample_4.txt)
   • The program will calculate all and result will be shown in console and respective text file.
   • In the end it will present its output.

• common settings that have used is shown along with all calculated data.

THE END.