Papers by Sushma Bahuguna
IFRSA’s International Journal Of Computing, 2015
Currently speech recognition has become multidisciplinary research area that has received great i... more Currently speech recognition has become multidisciplinary research area that has received great interest in improvement of human-machine interaction. The work leading to this paper has been focused on implementing emotion based text-independent, closed set, speaker identification system. Most of the studies in speech recognition have focused either on speaker identification or emotion recognition. The present experimental study addresses to combine the two tier identification of speaker and emotion using Gaussian mixture model that will extend the application area of speech recognition. The system is evaluated on recorded sample sentences of eight native Hindi speakers in five basic emotions i.e. Anger, Happiness, Neutral, Sadness and Surprise. Using this probabilistic model approach for selected sample sentences, the identification accuracy of 86% and 97% was achieved by emo-voice model for speaker with correct emotion identification and speaker identification respectively.
TIAS, 2010
Abstract: As the barriers of distances in networking are removed
through Internet technology. It ... more Abstract: As the barriers of distances in networking are removed
through Internet technology. It is the time to have new era in the field
of database, AI and IR and web. This is coming up in the form of
semantic Web .The word semantic define ‘meaning’. As the semantic
database is the latest trend in database technology and it is incorporating
the new generation of knowledge representation and Information
Retrieval for Semantic Web. This paper presents the in depth discussion
on Ontology based web, the transition from HTML to OWL .Information
Retrieval system and Semantic web.I will also be discussing the different
techniques used in IR systems for Semantic Web.
IAEME Publication, 2018
Audio Steganography is well known technique of hiding secrete text or audio information in host a... more Audio Steganography is well known technique of hiding secrete text or audio information in host audio by modifying an audio signal in an imperceptible manner. Least Significant Bit (LSB) is the most commonly used technique for secure data transfer in audio steganography. e present paper focusses on n Th th bit replacement to hide a sequence of bytes of secret text and comparing the MSE and PSNR of SteganoAudio for all the bits.
Smart card is not tamper proof but it is temper resistant and temper evident to a degree. Smart c... more Smart card is not tamper proof but it is temper resistant and temper evident to a degree. Smart card is widely used for business transactions and multiple services in a wide range of industries worldwide to support access, identity, payments and other applications. This paper presents an overview of attacks against smart card implementations and possible countermeasures for attacks that can give background for the assessment of the tools to improve security system of cards.
Abstract- Emotion based speaker Identification System is the process of automatically identifying... more Abstract- Emotion based speaker Identification System is the process of automatically identifying speaker’s emotion based on features extracted from speech waves. This paper presents experiment with the building and testing of a Speaker’s emotion identification for Hindi speech using Mel Frequency Cepestral Coefficients and Vector Quantization techniques. We collected voice samples of Hindi speech sentences in four basic emotions to study speaker’s emotion identification and it was found that with proposed emo-voice model we are able to achieve accuracy of 73 % of speaker’s emotion identification in speech out of 93 % of the total speech samples provided to the system.
A Study of Gender Specific Pitch Variation Pattern of Emotion Expression for Hindi Speech
The present study is an attempt to analyze the pitch variation pattern of Hindi emotional voice s... more The present study is an attempt to analyze the pitch variation pattern of Hindi emotional voice samples in five different emotional states. Sample sentences of male and female speakers were recorded in different emotions i.e. Neutral, Angry, Happiness, Sadness and Surprise. Emotion validation of sample sentences was done using machine recognizer and listening test. Pitch variation analysis of the statistics derived from the pitch contour on selected sample sentences was performed using PRAAT and MATLAB and results computed as mean, standard deviation, maximum and minimum pitch, pitch range, and peak parameters show a strong influence of pitch variation on the emotional state of the speakers. The analysis includes discriminating capability of pitch features in different emotions when gender information is taken into consideration.
A Study of Acoustic Features Pattern of Emotion Expression for Hindi Speech
Emotion is an affective state of consciousness that involves feeling and plays a significant role... more Emotion is an affective state of consciousness that involves feeling and plays a significant role in communication. There are objectively measurable voice parameters at physiological, articulatory - phonetics and acoustic levels that reflect currently experiencing affective emotional state of a person. Measurements at the physiological and articulatory-phonetics levels are invasive and require specialized equipments. Acoustic parameters of emotion expression can be obtained unremarkably from speech recording that allow speech emotion analysis and speaker’s emotion recognition inferences and hold important prospects for interdisciplinary research on emotional speech. In present study we analyzed feature pattern of acoustic parameters including pitch, duration, intensity and Formants based on the emotional speech sentences in Hindi classified according to auditory impressions and emotion based speaker identification system. Six speakers of different age group were chosen and twenty sa...
INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING AND TECHNOLOGY, 2019
Audio steganography is one of the important methods to transit hidden information
by modifying a... more Audio steganography is one of the important methods to transit hidden information
by modifying an audio signal in an imperceptible manner. In audio steganography, determining the best possible position for embedding the secret message with minimum
alteration of the cover audio remains a challenging issue. In this technique we hide
secrete text or audio information in a host message such that no one except the intended
receiver is aware of its existence and prevents unauthorised access. Various techniques
have been used for embedding information in digital audio. Least significant bit (LSB)
technique is most commonly used technique for secure data transfer. This paper
presents replacement of bits of samples to hide a sequence of bits of secrete text. The
bits of samples are selected in a circular manner from LSB to MSB or vice versa. The
results reveal satisfactory performance of the system and may be used for secure
movement of data.
International Journal of Computer Science Issues
This paper describes a text independent, closed set, speaker identification system to identify th... more This paper describes a text independent, closed set, speaker identification system to identify the speaker along with the emotional expression (Emo-voice Model) of the particular speech sentence. The system is evaluated on recorded sample sentences of native Hindi speakers in five basic emotions. Spectral Features, Mel Frequency cepstral coefficients have been used to implement emo-voice models using Vector Quantization and Gaussian Mixture modeling techniques for selected sample sentences using MATLAB. The VQ model trained with K-mean algorithm achieves as much as 82.7% of speaker identification with correct emotion accuracy whilst GMM model trained with EM algorithm achieves 87.9% of speaker identification with correct emotion accuracy. The statistical approach of Emo-voice Models could be used to extend the application field of voiceprint recognition technology.
Performance Evaluation of Speaker Identification System for Male Speaker During Adolescence
A voice mutation commonly refers to the deepening of voice of people from early to late adolescen... more A voice mutation commonly refers to the deepening of voice of people from early to late adolescent stages. Males experience a more dramatic voice mutation than females during adolescence. This paper presents experiment for performance evaluation of speaker identification system for male speaker during adolescent stages. A text independent, closed set speaker identification system is implemented using MelFrequency Cepstral Coefficients (MFCC) and Dynamic Time warping (DTW) algorithms in MATLAB for training and testing of recorded short sample sentences of native Hindi male speaker during adolescent stages for speaker identification accuracy. The system achieved approx 98% speaker identification accuracy for the speech sentences trained against sample sentence of corresponding age but speaker identification performance was insignificant when trained speech sample sentence was of different age from the age of testing speech sentences. The results show strong influence of voice mutation...
Emotion based speaker Identification System is the process of automatically identifying speaker’s... more Emotion based speaker Identification System is the process of automatically identifying speaker’s emotion based on features extracted from speech waves. This paper presents experiment with the building and testing of a Speaker’s emotion identification for Hindi speech using Mel Frequency Cepestral Coefficients and Vector Quantization techniques. We collected voice samples of Hindi speech sentences in four basic emotions to study speaker’s emotion identification and it was found that with proposed emo-voice model we are able to achieve accuracy of 73% of speaker’s emotion identification in speech out of 93% of the total speech samples provided to the system.
IAEME PUBLICATION, 2019
Audio steganography is one of the important methods to transit hidden information by modifying an... more Audio steganography is one of the important methods to transit hidden information by modifying an audio signal in an imperceptible manner. In audio steganography, determining the best possible position for embedding the secret message with minimum alteration of the cover audio remains a challenging issue. In this technique we hide secrete text or audio information in a host message such that no one except the intended receiver is aware of its existence and prevents unauthorised access. Various techniques have been used for embedding information in digital audio. Least significant bit (LSB) technique is most commonly used technique for secure data transfer. This paper presents replacement of bits of samples to hide a sequence of bits of secrete text. The bits of samples are selected in a circular manner from LSB to MSB or vice versa. The results reveal satisfactory performance of the system and may be used for secure movement of data.
Uploads
Papers by Sushma Bahuguna
through Internet technology. It is the time to have new era in the field
of database, AI and IR and web. This is coming up in the form of
semantic Web .The word semantic define ‘meaning’. As the semantic
database is the latest trend in database technology and it is incorporating
the new generation of knowledge representation and Information
Retrieval for Semantic Web. This paper presents the in depth discussion
on Ontology based web, the transition from HTML to OWL .Information
Retrieval system and Semantic web.I will also be discussing the different
techniques used in IR systems for Semantic Web.
by modifying an audio signal in an imperceptible manner. In audio steganography, determining the best possible position for embedding the secret message with minimum
alteration of the cover audio remains a challenging issue. In this technique we hide
secrete text or audio information in a host message such that no one except the intended
receiver is aware of its existence and prevents unauthorised access. Various techniques
have been used for embedding information in digital audio. Least significant bit (LSB)
technique is most commonly used technique for secure data transfer. This paper
presents replacement of bits of samples to hide a sequence of bits of secrete text. The
bits of samples are selected in a circular manner from LSB to MSB or vice versa. The
results reveal satisfactory performance of the system and may be used for secure
movement of data.
through Internet technology. It is the time to have new era in the field
of database, AI and IR and web. This is coming up in the form of
semantic Web .The word semantic define ‘meaning’. As the semantic
database is the latest trend in database technology and it is incorporating
the new generation of knowledge representation and Information
Retrieval for Semantic Web. This paper presents the in depth discussion
on Ontology based web, the transition from HTML to OWL .Information
Retrieval system and Semantic web.I will also be discussing the different
techniques used in IR systems for Semantic Web.
by modifying an audio signal in an imperceptible manner. In audio steganography, determining the best possible position for embedding the secret message with minimum
alteration of the cover audio remains a challenging issue. In this technique we hide
secrete text or audio information in a host message such that no one except the intended
receiver is aware of its existence and prevents unauthorised access. Various techniques
have been used for embedding information in digital audio. Least significant bit (LSB)
technique is most commonly used technique for secure data transfer. This paper
presents replacement of bits of samples to hide a sequence of bits of secrete text. The
bits of samples are selected in a circular manner from LSB to MSB or vice versa. The
results reveal satisfactory performance of the system and may be used for secure
movement of data.