Speech Processing for Low Resource Scenarios I - Day 8
Center for Language & Speech Processing(CLSP), JHU via YouTube
AI Product Expert Certification - Master Generative AI Skills
Free courses from frontend to fullstack and AI
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore speech processing techniques specifically designed for low-resource language scenarios through this comprehensive tutorial presentation from the Johns Hopkins University Summer Workshop on Language and Speech Technologies (JSALT 2025). Learn fundamental approaches and methodologies for developing speech processing systems when working with limited data, covering challenges unique to under-resourced languages and practical solutions for overcoming data scarcity. Discover strategies for leveraging transfer learning, cross-lingual techniques, and data augmentation methods to build effective speech recognition and processing systems for languages with minimal training resources. Gain insights into the theoretical foundations and practical implementations that enable speech technology development in linguistically diverse but data-poor environments.
Syllabus
[slides] Day 8 morning - JSALT 2025 - Mdhaffar: Speech Processing for Low Resource scenarios I.
Taught by
Center for Language & Speech Processing(CLSP), JHU