Language technology for linguistswith Internet of Things (IoT)

Ahilesh Kakolu Ramarao, Winter 2022, Course Catalog

Course Description

Have you ever wondered why Voice Assistants (Siri, Amazon Echo and Google Assistant) could not quite understand your English accent? We, as linguists, can play an important role as evaluators of such complex systems. Through this beginner-friendly course, you will open up the black box of language technology by building them with mini-portable computers. In the process, you will acquire new digital skills that complement your linguistic training. Specifically, you will be given the unique opportunity to apply your English and linguistic knowledge for building everyday language technology applications such as evaluating the voice assistant’s ability to perceive and produce different English accents, prosody patterns, styles, and emotions. You will be primarily working with mini-portable computers, NVIDIA® Jetson Nano Developer Kit. With the NVIDIA Kits, you will build an interactive machine that can speak (Speech Synthesis - convert written text into spoken speech) and can listen (Speech Recognition - transcribe spoken speech into written text). Furthermore, you will evaluate automated systems using linguistic analysis and provide you an opportunity to come up with novel linguistically-motivated evaluation methods. Prior programming knowledge is NOT required. You would be provided with instructions on developing these technologies and basic programming knowledge will be introduced as needed. Throughout the course, the focus will be on whether these language technologies can learn human-like linguistic abilities. At the end, you would be equipped to build your own interactive Speech Synthesizer and Speech Recognition systems with the NVIDIA devices.

Pre-requisites: None, except the willingness and enthusiasm to learn about language technologies and linguistics. Please bring your laptop for each session.

Outcomes: During the course, you will gain a comprehensive overview of the technical basics of speech technology, learn various statistical tools and understand the basics of Hardware/Software interaction. These digital skills are the most sought-after ones in the language technology industry.