Project Assistant

Ronanki Srikanth, +91-991*******, *******.********@*****.***

http://researchweb.iiit.ac.in/~srikanth.ronanki/

Areas of Interest My interests primarily lie in Audio Signal Processing, Pattern Recognition, Spoken Language

Processing and Image Processing.

Education IIIT-Hyderabad 2007 - Present

MS by Research Advisor: Dr. Kishore Prahallad

Speech and Vision Lab CGPA: 8.25

B.Tech (hons) in Electronics and Communications CGPA: 7.1

Narayana Junior College, Nellore 2004 - 2006

Senior Secondary 95%

St. Judes Public School, Srikakulam 2003 - 2004

SSC 92%

Work Experience Google Summer of Code Intern

Freelancer, Hyderabad Summer 2012

Designed a web based Pronunciation Evaluation scroing routine using CMUSphinx which pro-

vides necessary feedback on mispronunciation at phone/word level. Worked with CMUSphinx

organization in USA.

Akshar Speech Technologies Pvt. Ltd. Intern

Vindhya C-4, CIE, Hyderabad Summer 2011

Developed a software for speech enhancement which can de-noise the speech in di erent envi-

ronments. Also worked as senior web developer for Akshar Speech Products release.

Speech and Vision Lab Research Assistant

IIIT, Hyderabad 2009 - Present

Explored into several research elds in Speech Signal Processing, image processing and machine

learning areas. Major part of my work belongs to Voice Duration Modelling, Accent Modelling

and Voice Conversion.

IIIT Hyderabad Teaching Assistant

IIIT, Hyderabad 2012 - Monsoon

Teaching assistant for the course Computer Programming in Monsoon, 2012.

Virtual-Labs, EnhanceEdu Project Assistant

IIIT, Hyderabad Nov 2009 - June 2010

Developed a ash project for algorithms in data structures. Developed a ash project for class

room environment presentation and FAQ section in ash.

Publications Ronanki Srikanth, Kishore S. Prahalladi and Peri Bhaskararao. Acoustic correlates of syllable-

level prominence in Telugu ACL-2012, ICC JEJU, Republic of Korea, 08-14, July 2012. [Re-

jected]

Srikanth Ronanki, Bajibabu B, Kishore Prahallad. Duration Modelling In Voice Conversion

Using Arti cial Neural Networks International Conference on Systems, Signals and Image Pro-

cessing, Vienna, Austria, April 2012 (Published)

Bajibabu, Ronanki Srikanth, Sathya Adithya Thati, Bhiksha Raj, B Yegnanarayana, Kishore

Prahallad. A comparison of prosody modi cation using instants of signi cant excitation and

mel-cepstral vocoder Centenary Conference of the Indian Institute of Science, 14-17 Dec 2011,

Banglore (Published)

Thesis and Extraction of cues for Language Identi cation and automatic Prominece detection

Related Projects Guide: Dr. Kishore S Prahallad

Automatic Language Identi cation can be used as pre-processing for either machines or human-

listeners. In this thesis, I analysed di erent Indian languages based on prosodic and spectral

information. Unless like International Languages, most of the Indian Languages share a similar

phoneme set. The discrimination of Indian Languages at word level is a challenging problem.

Therefore, I extracted cues based on phoneme durations, intonation, intensity, rhythm and

stress. Later I use these di erences in modelling the speech to change the accent and to detect

the prominence automatically.

Duration Modelling In Voice Conversion Using ANN Semester Project, 2011

Guide: Dr. Kishore S Prahallad

Voice conversion aims at transforming the characteristics of a speech signal uttered by a source

speaker in such a way that the transformed speech sounds like the target speaker. Such a con-

version requires transformation of spectral and prosody features. In this project, we propose a

technique for duration transformation of source speaker to that of a target speaker. This work

is done in the framework of Arti cial neural networks based voice conversion. The results are

evaluated using subjective and objective measures con rm that incorporating durational modi-

cation to voice transformation improves the voice quality and has the characteristics of target

speaker.

A Comparison of Prosody Modi cation Using two methods Semester Project, 2010

Guide: Dr. Kishore S Prahallad and B Yegnanarayana

In this project, we compare two methods for prosody (duration and pitch) modi cation. Those

two methods are prosody modi cation using instants of Signi cant Excitation and Mel-Cepstral

vocoder. We show that duration modi cations are better using Mel- Cepstral vocoder for higher

modi cation factor while pitch modi cations are better using instants of Signi cant Excitations.

In the end we show that Mel-Cepstral vocoder provides exibility for non-uniform prosody ma-

nipulation

Hand-written Digits Recognition Course Project 2010

Guide: Dr. Anoop

In this project, we showed how to solve the problem of classifying the handwritten numeric

characters (0-9). For this we will be using classi er tool called lnknet that does the classi cation

based on the input features that are extracted from each image using ANN classi er. So, our

main aim is to derive the most desirable features from each image for classi cation. Di erent

features have been extracted and rst the classi er is trained with the extracted features. When

a test image is presented, classi cation is done based on the extracted features from the test

image.

Pronunciation Checker Winter School Project, 2009-2010

Guide: Dr. Biksha Raj

This Project involved implementation of a pronunciation checker. In this project we had taken

the correct pronunciation word as reference and then we compared with the input. Compari-

son was done by using DTW (Dynamic Time Wrapping) algorithm, VQ (Vector Quantization)

codebook approach.

Phoneme Boundaries based Automatic Speech Segmentation Summer 2009

Guide: Dr. Kishore S Prahallad

In this project, we proposed an algorithm used to automatic speech segmentation and labelling

for English speech database. In our proposed method, the dissimilarity(di erence between two

consecutive frames) process is rst performed on speech feature to obtain more robust feature

and then we applied a threshold value to decide segmentation points. Experiment results show

that our proposed method can e ciently detect up to 70 percentage. The accuracy of results

are further increased by using more segmentation techniques.

Morphological Background Detection and Enhancement Course Project 2009

Guide: Dr. Jayanthi Sivaswamy

In this project, we rst detected the background of the image using various methods. Using

the background detected and comparing it with the original image, we did a non-linear mapping

of the pixel intensities to get an enhanced image.

Other Projects Design of GUI for audio recording and manipulations

Design of 3D Building using OpenGL

Design of Asteroid Shooter Game using OpenGL

Design of Inter-College Football Tournament Website

Design of Courier Portal for IIIT-H

Design of Tra c Controller Using Ultra-Sonic Sensors

Programming Languages : C, C++, python

Technical Skills

Scripting Languages : Python, Shell scripting

Web Technologies : HTML, CSS, PHP, Javascript(Basic)

Database Management : MySQL

Libraries and Tools : Matlab(Advanced), L TEX, Adobe Photoshop CS4, Adobe Flash CS4, AS3,

A

Microsoft Visual Studio, OpenGL, Netbeans.

Operating Systems: GNU/Linux, Windows.

Achievements Recipient of Research award for the Academic year 2010 - 11.

Awarded for Excellence in System Administration for the Academic year 2010-11

Awarded for Excellence in Secondary School Examination by St.Judes Public School.

Conferences & Attended Centenary Conference, IISc Bangalore (CCEE 2011)

Workshops

attended Volunteered and Attended Conference on Data Mining (PAKDD 2010)

Winter School On Speech and Audio Processing (WISSAP 2012)

Workshop on Image and Speech Processing (WISP 2010,11)

Graphics Pattern Recognition

Course Work

Signals & Sysytems Electro-Magnetic Theory

Digital Signal Processing Information Theory & Coding

Arti cial Neural Networks Computer Programming

Digital Image Processing Data Structures

Speech Signal Processing Number Theory

Time Frequency Analysis Linear Algebra

Extra-Curricular Students Finance Secretary of IIIT-H from 2009-11

Activities

System Administrator for Courier Portal in IIIT-H from 2009-present

Worked in the Web Design Team for Felicity 2K10

Member of a Volleyball Team and Football at Intra-college level.

Personal Details Hobbies : Sports, Photography, Trekking.

Languages : English, Telugu, Hindi.

Current Address : OBH 270, IIIT-H, Gachibowli,Hyderabad-500032, India.

Date of Birth : 22-06-1989.

Referees Available upon request

Contact this candidate