1

Table of Contents:

Introduction.....................................................................................2

Approach......................................................................................3-4

Program Development....................................................................5

Project Data and Results...........................................................6-10

Conclusions...................................................................................10

Source Code for C application......................................................A

Matlab Source Code.......................................................................B

2Introduction (Quick Story):

The general public is constantly offered a barrage of new (as well as old

disguised as new) music for their consumption by the record industry. Whether it

be a new song by a popular artist or a old classic that the listener has never

heard before, it is often difficult to tell if it is worthy of valuable time and money of

the listener.

Music in the more traditional sense has been on the decline for the past

century. The first part of the 20th century saw a growing interest in dance music

and thus the “Big Band Era.” Big bands, arguably for the first time in musical

history, became the “POPular Music.” Famous ones such as Glen Miller, Benny

Goodman, and the Dorsey Brothers (to name only a few) succeeded in selling

records in large numbers. At no other times after these periods (1920's ~ 1950's)

have single bands dominantly control the entire music industry for extended

periods of time.

And so we now enter the modern “Rock” era, which came to replace the big

bands. It became possible for Rock to gain a firm foothold in the popular music

due to its more raunchy and rebellious nature with which a new generation found

liberation. Many blamed artists such as Woody Herman and Stan Kenton, the

last of the big bands, for promoting singers in their bands whose popularity

eventually started to overshadow the musicians. The rock era introduced music

with a much more poetically cerebral quality due to bands featuring singers with

LYRICS to express messages to listeners.

The prominence of lyrics in modern music allows for music to enter the realms

relevant to this project. The new style gives music, a highly subjective entity, a

new aspect which can be studied analyzed to form objective measurements.

Using characteristics derived from these lyrics, a MLP can be trained to an

individual's preferences and used to judge whether a song is viable for the

listener's ear.

3

Basic Approach:

It is up to the listener to decide what music is worthy of purchasing and what is

not worth the time and money. Assuming that the listener is intelligent and brave

enough to have his or her own opinion (with or without succumbing to peer

pressure), this project will attempt to provide a useful tips for the would-be music

consumer to make a decision on whether a given song by a particular group is

worth listening to.

This program primarily focuses on breaking down the lyrics of a song. The lyrics

of the song is where an artist conveys his/her emotions, intelligence, and deep

underlying messages. I understand that the very way the artist sings the lyrics

( stressing of certain notes, facial expressions, etc.) also convey the things

mentioned above but the lyrics are the only real part of a song that can be

analyzed and quantified easily within the scope of this class.

Quantified Data will include:

•% of unique words – bad artists often end up repeating the same lyrics over and over which often suggest the artist has nothing really intelligent or worthy to say.

•The very number of unique words, also may help in developing the MLP

•Count of key words – I find that bad pop artists abuse and overuse particular words such as LOVE, BABY, HEART, FEEL, etc.

•Word length – Sophisticated, intelligent artist will use bigger multi-syllabled words. This may point towards more meaningful lyrics.

The MLP Classifier predicts a music's category into different groups ranging from

BAD to GOOD. Many possibilities were explored. Eventually, I settled on a MLP

that dealt with 5 input features, and only 2 classifications (Good, Bad). The

results and conclusions of research/experiments are contained in the following

sections.

4

How many categories in between (e.g. OK, MARGINAL), depended on the

performance of the MLP during the developmental stages of the project.

I trained and tested with cross validation techniques used in some of the class

assignments. The baseline value achieved using the knearest neighbor

algorithm was somewhere between 25 to 30 % error rate making it have a 70 to

75% classification rate. A decent figure to shoot for.

5

Program Development

The project specification required me to develop an application that took in raw

data in the form of lyrics (plain text files) and process them for the required data.

This C application was developed and tested using Microsoft's .NET

Developmental Environment.

The steps required to be performed on the data where:

•Traversal of the current directory structure in search of proper lyrics files.

•Parsing and insertion of lyrics into an array data structure•Filtering of extraneous characters that skew data (punctuation).•Analysis of data structure of uniqueness, avg length, and so forth.•Output to data file with format compatible with MLP matlab program.

Details of development are included in the remarks of the source code attached

in the appendix. Next, the MLP program provided by the class website was

augmented to fit the needs of this project's specifications. The neural network's

input were automated with variables defined in the upper portion of code and the

entire structure looped for efficiency.

Initial experiments were run with a 3 classification data sets. The input features

defined as:

1.Number of lyrics2.Number of unique lyrics3.% of Lyrics that are unique4.Avg length of lyrics5.Total number of Characters

This program is intended to be trained by the consumer to his/her taste in music

and so a bit of subjectivity is required for the completion of the classification of

training data. Out of the vast universe of lyrics I could have chosen from, I

decided to pit in what is my opinion, good music versus really bad music. These

songs being from 2 different eras: 60's,70's Rock and Late 90's “Pop Music.” I

collected numerous lyrics of songs by the classic artists I knew: The Beatles,

Pink Floyd, and Jimi Hendrix. For the pop music, I decided to go with the current

sensations: N'Sync, Backstreet Boys, and Britney Spears. At

6

http://www.sing365.com/ a free lyric web site for many popular artist, I obtained

data on 2 groups of music and ran them through my compiled C program

application. (The data and training files available in the appendix)

The data in the matlab program was normalized since the feature vectors' mean,

variance and max,min values differed greatly.

Training Data mean variance min maxFeature Vector 1 177.8125 4607 39 325Feature Vector 2 79.3125 1358 26 138Feature Vector 3 697.7500 64832 209 1240Feature Vector 4 3.9975 0.1731 3.61 5.3600Feature Vector 5 27.4294 270.4976 0.73 53.8500

The first results obtained were quite awful to say the least. The classification

rates on the training were at acceptable ranges of upwards to about 90% but the

classification of the test data were unacceptably low:

Failed convergence

Variable number of hidden layer w/ α = 0.1 and 5 neurons/layer# of Hidden Layers 2 3 4 5 6 7 8 9 10Training Crate (%) 90.0000 84.2857 88.5714 84.2857 82.8571 82.8571 82.8571 82.8571 82.8571Testing Crate (%) 37.5000 68.7500 37.5000 56.2500 31.2500 43.7500 31.2500 31.2000 31.2000

7

Variable number of neurons/hidden layer w/ α = 0.1 and 3 hidden layers# of neurons/layer 1 2 3 4 5 6 7 8 9 10Training Crate (%) 82.8571 85.7143 87.1429 88.5714 91.4286 95.7143 95.7143 92.8571 91.4286 91.4286Testing Crate (%) 31.2500 31.2500 31.2500 31.2500 43.7500 31.25 56.2500 50.0000 50.0000 56.2500

8

The best Test classification rate achieved in the 1st experiment was 68.75% and

most were below 50% making these results inadequate to the task. Similarly, for

the 2nd run where the number of neurons/layer were changed, the best test data

classification rate achieved was only ~56%. I analyzed the results and with the

correlating data and found that the main inconsistency was with the middle

classification: the OK class: between Good and Bad. Thus I reevaluated what

parameters of the specification I could change to improve the performance of the

classification rate. I decided to remove the mid-rating and go with either Good or

Bad. As I looked through the feature vectors of the data, I found 2 key

characteristics in the feature vectors within the data file that correlated well with

my ratings (classifications) They were the character length and the % unique

lyrics features. The character length tended to be lower and % unique feature

higher for lyrics that were given a higher classification rating. Therefore, I

decided that removing ambiguities introduced by 3 classes instead of 2 was a

good way of improving my MLP performance. After altering the original C

application to output only 2 classifications, the results were much better:

10

Variable number of hidden layer w/ α = 0.1 and 5 neurons/layer# of Hidden Layers 2 3 4 5 6 7 8 9 10Training Crate (%) 100 100 97.1429 95.7143 95.7143 95.7143 95.7143 95.7143 80Testing Crate (%) 87.0968 90.3226 96.7742 93.5484 93.5484 93.8454 61.2903 87.0968 61.2903

Variable number of neurons/hidden layer w/ α = 0.1 and 3 hidden layers# of neurons/layer 1 2 3 4 5 6 7 8 9 10Training Crate (%) 88.5714 95.7143 100 97.1429 100 100 100 100 100 100Testing Crate (%) 80.6452 93.5484 93.5484 90.3226 96.7742 93.55 93.5484 93.5484 90.3226 87.0698

# of neurons/layer 11 12 13 14 15Training Crate (%) 100 100 100 100 100Testing Crate (%) 93.5484 90.3226 74.1935 96.7742 93.5484

12

Conclusions:

In the end, I found that the optimal settings for the MLP were setting:

•alpha = 0.1

•momentum = 0.8

•hidden layer = 3

•neurons / layer = 5

classification = 96.7742%

These values resulted in the optimum results having near convergence during

training and a test data classification rate of nearly as high as the training

classification rate. I was able to achieve a classification rate that exceeded the

baseline case using the k-nearest neighbor algorithm.

Appendix A-1/*******************************************************************************

ECE 539 PROJECT

Author: Koji YabumotoName: ece539prj.c current: version 5.3

History: 1.0 2003 - 11 - 03 Started1.1~1.4 2003 - 11 - 04~06 Visits every file in directory2.0~2.1 2003 - 11 - 15 Detects lyrics files only.3.0~3.4 2003 - 11 - 15 Calculates number of chars,

lyrics and avg length.4.0 2003 - 11 - 16 Calculates number of unique

words.4.1 2003 - 11 - 22 Calculates % of unique words5.0~5.2 2003 - 12 - 01 prints out results to file5.3 2003 - 12 - 06 Input rating from user5.4 2003 - 12 - 15 Classification down to 2

Description:This program is part of the ECE 539 project thattakes lyrics from songs in a particular directory and analyzes them for certain characteristics and thenformats them for the MLP matlab program to use.

Notes: This program file was compiled and developed in Windows XPusing the:

-- Microsoft Development Environment 2002 ver. 7.0.9492Copyright 1987-2001 Microsoft Corp.

Microsoft .NET Framework 1.0 ver. 1.0.3705Copyright 1998-2001 Microsoft Corp.

The executable that results is thus meant to be run in acommand prompt in the Windows environment.

*******************************************************************************/#include <stdio.h>#include <string.h>#include <stdlib.h>#include <windows.h>

void prjError(int e);int chew_lyrics(char *filenamebuf,char *pLastName);int process_file(char *filenamebuf, char *pLastName);int detect_lyr(char* filenamebuf);int load_lyrics(char *filenamebuf, char *pLastName);int unique_count();

int parse_load(char* ibuf);int number = 0;int number_u = 0;int rating1 = -1;FILE *DataFile;char version_number[14] = " 5.3";

typedef struct {char data[30];//data[0] = '\0';

}aWord;

aWord words[5000];aWord not_unique[5000];char* write_file = "lyric_data.txt";

A-2int main (int argc, char* argv[]){

char filenamebuf[MAX_PATH];char* pLastName;HANDLE hfind;WIN32_FIND_DATA fdata;

DataFile = fopen(write_file,"a");

if(argc == 2 && (strcmp(argv[1],"/?")) == 0){prjError(2);return(0);

}else if (argc > 1){prjError(1);return(1);

}//else ifprintf("note: 1st valid character (either 1,2,or3) will be used.\n");if(GetFullPathName("*",

sizeof(filenamebuf),filenamebuf,&pLastName)){

hfind = FindFirstFile(filenamebuf, &fdata);if (hfind != INVALID_HANDLE_VALUE){

do{if (fdata.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)

continue;strcpy(pLastName, fdata.cFileName);if (process_file(filenamebuf, pLastName))

return(1);

}while(FindNextFile(hfind, &fdata));FindClose(hfind);

}

}//if

fclose(DataFile);printf("DONE\n");return(0);

}//main

int process_file(char *filenamebuf, char *pLastName){

int i= 0;//printf("filename: %s", pLastName);if (!detect_lyr(filenamebuf)){

//printf("note: 1st valid character (either 1 or 2) will be used.\n");printf("%s Rating(1=BAD, 2=GOOD):",pLastName);//i = scanf("%d", &rating1);i = getchar();fflush(stdin);//printf("-----%d---\n",i);//if (i == 10)// i = getchar();while(i < 49 || i >50){

if( i != 10 )printf("error:(1=BAD, 2=GOOD):");

i = getchar();fflush(stdin);//if (i == 10)// i = getchar();

//i = scanf("%d", &rating1);}rating1 = i - 48;chew_lyrics(filenamebuf, pLastName);

}

return(0);}void prjError(int e){

if(e == 1){printf("ece539prj %s: USAGE ece539prj\n",version_number);

}else if(e == 2){printf("ece539prj %s: USAGE ece539prj\n",version_number);printf(" This program takes all files with .lyr extentions\n");printf(" in current directory and asks user for rating of song.\n");printf(" Then program puts data into a file for MLP program.\n");

}

}//prjError

/******************************************************load_lyrics()

Loads lyrics into word array.******************************************************/int load_lyrics(char *filenamebuf, char *pLastName){

FILE *ReadFile;char ibuf [16000];int k;number = 0;ReadFile = fopen(pLastName, "r");

if(!ReadFile){printf("ece539prj: Could not open file %s\n",pLastName);return(1);

}while (fgets(ibuf,sizeof(ibuf),ReadFile)){

for (k = 0; k < sizeof(ibuf); ++k){if (ibuf[k] == ',' || ibuf[k] == '.' || ibuf[k] == '?' ||

ibuf[k] == '!' || ibuf[k] == '(' || ibuf[k] == ')' || ibuf[k] == '-' || ibuf[k] == '"')ibuf[k] = ' ';

}parse_load(ibuf);

}fclose(ReadFile);return(0);

}

/****************************************************parse_load();

parses one line and loads it into array ****************************************************/int parse_load(char* ibuf){

char* single;single = strtok(ibuf, " \t\n");

if (single == NULL)return(0);

strcpy(words[number].data , single);

number++;while(single != NULL){

single = strtok(NULL," \t\n");if (single == NULL)

return(0);strcpy(words[number].data, single);number++;

}

return(0);}

A-3/*******************************************************

chew_lyrics()

Extract desired statistics from lyrics.*******************************************************/int chew_lyrics(char *filenamebuf,char *pLastName){

int i;int number_lyrics = 0;int unique = 0;int characters = 0;double avg_len,percent;char rater[7] = "0 0 0";

//load lyrics firstload_lyrics(filenamebuf, pLastName);

//get statsnumber_lyrics = number; // number of wordsfor (i = 0; i < number_lyrics; i++){ // number of characters

characters += (int)strlen(words[i].data);}if (number_lyrics != 0)

avg_len = ((double)characters)/((double)number_lyrics);else

avg_len = 0;

unique = unique_count();percent = ((double)(unique))/number_lyrics * 100;

printf("Lyrics: %d Different Lyrics: %d Chars: %d Avg Len: %.*f percent unique: %.*f\n",number_lyrics,number_u, characters,2,avg_len,2,percent);if (rating1 == 1)

strcpy(rater,"\t0\t1");else if (rating1 == 2)

strcpy(rater,"\t1\t0");

//else if (rating1 == 3)// strcpy(rater,"\t1\t0\t0");fprintf(DataFile, "%d\t%d\t%d\t%.*f\t%.*f%s\n",number_lyrics, number_u, characters,2,avg_len,2,percent,rater);

return(0);}

/**********************************************************unique_count();

**********************************************************/int unique_count(){

int number_not = 0;int number_total = 0;int i,j,k, flag, first;int uniqueness = number;flag = 0;first = 0;//printf("Number: %d\n",number);for (i = 0; i < number-1 ; ++i){

//printf("i: %d\n",i);for (k = 0; k < number_not; ++k){

if(!strcmp(words[i].data,not_unique[k].data)){//printf("already good\n");flag = 1;

break;}

}if (flag == 1){

flag = 0;}else{

for (j = i+1; j < number; ++j){

A-4//printf("%d %s %s\n",i,words[i].data,words[j].data);if(!strcmp(words[i].data,words[j].data) && first == 0){

//printf("first time\n");first = 1;strcpy(not_unique[number_not++].data, words[i].data);uniqueness-=2;++number_total;

}else if(!strcmp(words[i].data,words[j].data) && first == 1){--uniqueness;++number_total;

}}

}first = 0;

}

//for (k = 0; k < number_not; ++k){// printf("--%s\n",not_unique[k].data);//}

//printf("not:%d total:%d uniqueness:%d\n",number_not,number_total,uniqueness);number_u = number - number_total;//not_unique;

return(uniqueness);}

/**********************************************************detect_lyr()

Determines if file name has .lyr extention.**********************************************************/int detect_lyr(char* filenamebuf){

int i;char extention[5] = ".lyr\0";char copy_a[5];char* a = &filenamebuf[(int)strlen(filenamebuf) - 4];

strcpy(copy_a, a);for (i = 0; i < 4; ++i){

if (copy_a[i] >= 'A' && copy_a[i] <= 'Z')copy_a[i] += 32;

}//printf(" extention: %s ", copy_a);if (strcmp(copy_a, extention))

return(1);return(0);

}