Objectives:
- The main objective of the Seasonal school is to provide a platform to create awareness on recent developments in Signal Processing and its applications to the latest technological developments using machine learning techniques.
- To allow the participants a wide scope of opportunities in research and career , a well-curated course covering the recent advances and latest techniques, novel and innovative applications are also included in the lectures’ agenda.
- Foster membership development among young researchers with interests in signal processing and its applications.
Target audience:
- SPS members, Academic faculty, Persons from Industry, Research scholars, practitioners, PG students who have a strong focus on Signal processing.
About the program:
- This three-day intensive School will delve into the cutting-edge realm of speech and audio processing, with a particular focus on advancing human-machine interaction.
- Attendees will gain hands-on experience with state-of-the-art deep learning architectures, feature extraction techniques, and evaluation metrics.
- The curriculum will cover a wide range of topics, including end-to-end speech recognition, audio signal processing, and speech synthesis.
- Participants will have the opportunity to explore emerging trends such as multimodal learning and explainable AI.
- By combining theoretical knowledge with practical applications, this school aims to equip attendees with the skills and knowledge necessary to develop innovative speech and audio-based solutions.
Structure of the Program:
The school offers lectures, simulation studies and interactive sessions that provide knowledge and give participants the chance to exchange about their own ideas.
Resource Persons: From IITs/IIITs/NITs/Organizations of High Repute.
Venue: Matrusri Engineering College, Hyderabad,Telangana State, India.
Topics that will be dealt during the Seasonal school:
-
Topics:
Day 1: Foundations and Speech Processing
- Introduction to Speech and Audio Signals: Basic concepts, digital representation, and signal processing fundamentals.
- Speech Analysis and Feature Extraction: MFCCs, PLP, and other relevant features.
- Speech Recognition: HMM-based and DNN-based systems, challenges, and applications.
Day 2: Advanced Speech Processing and Audio Processing
- Speaker Recognition and Verification: Techniques, challenges, and applications.
- Text-to-Speech Synthesis: Traditional and neural-based methods, evaluation metrics.
- Introduction to Audio Signal Processing: Basic concepts, time-frequency analysis, and audio features.
Day 3: Human-Machine Interaction and Emerging Trends
- Speech and Audio in Human-Machine Interaction: Applications in virtual assistants, smart homes, and automotive systems.
- Challenges and Opportunities: Noise robustness, multilingualism, privacy, and ethics.
- Emerging Trends: Deep learning advancements, multimodal interaction, and industry perspectives.
Registration fee:
- Industry Participants: 1500
- Faculty Members (Non-IEEE): 750
- Faculty Members (IEEE): 500
- Research Scholars: 400
- Student Members (Non-IEEE): 300
- IEEE Student Members: 200
Registration Link: https://forms.gle/RuShRtK6fmveEkKYA
MECS IEEE SB (STB17791) Account Details:
A/C Name: IEEE MEC SB
A/C N0.: 052110100156962
UNION BANK OF INDIA
Saidabad Branch
IFSC Code: UBIN0805211
Coordinators:
- Dr. I. Sharath Chandra,
Assoc. Professor, ECE,
Matrusri Engineering College.
Mobile:9885391926
- Mr. K. Manohar,
Assistant Professor, ECE,
Matrusri Engineering College.
Mobile:9010858595
E-mail: mecsieeespsseasonalschool@gmail.com
