LANG 2091

Phonetics and Speech Technology

Course Description

Have you ever wondered how Siri understands your commands, why Alexa sounds like a real person, or how your smartphone recognizes your unique voice? Speech technology is everywhere, but it all starts with the science of human sound. LANG 2091 is an exciting, beginner-friendly broadening course that bridges the gap between human language and artificial intelligence. You don’t need any prior background in linguistics or coding. Instead, you will learn how to visually map human speech using spectrograms, decode the International Phonetic Alphabet (IPA), and understand the physical properties of sound. Whether you are majoring in engineering, business, science, or the humanities, this course will give you a unique, competitive edge by showing you how human-AI interaction actually works behind the screens.

Highlights

User-friendly acoustic software to literally see sound.
Learn to read spectrograms and conduct computerized acoustic analyses of your own voice and others, turning invisible soundwaves into readable data.

Personalized mini-research project.
Choose a “non-standard” speech sample that interests you - such as synthesized AI speech, a specific regional dialect, or code-switched bilingual speech - and compare it to “standard” speech using the acoustic analysis skills you’ve learned.

Assessment

  • Final project: explore topics of interests or relevance (e.g. synthesized speech, code-switching, foreign accents)
  • Out-of-class work: small group-based tasks to develop skills for the final project
  • Other assessments: two in-class tests

Target Students

  • No prior knowledge of phonetics or speech technology needed.

  • This course would appeal to any student interested in technology, AI, business innovation, engineering solutions, neuroscience research, or communication; these are fields of direct practical applications for this topic. 

Learning Experience

Student testimonials

  • “The course is well suited for an introduction to phonetics and acoustics technology for any backgrounds, enough to give a sense of what the subject is about while not overwhelmed with too much technical details.”
  • “The lab assignments are very interactive that allow students to grasp a more realistic understanding of the course materials.”
  • “Her teaching made use of multi-modal methods and made a very good attempt in connecting the content with what's trending amongst students nowadays.”
  • “I'm quite happy about the whole course ... I'm from CS and learn about NLP and spoken language processing, but didn't dive too deep into how speech is produced. This course helped complete the whole journey by letting me learn the entire process. I feel very delighted.”

Practical applications

Speech technology has applications in many fields:

  • Engineering: Enhance speech technology systems, design human-computer interfaces, or improve voice recognition software.
  • Science: Advance research by analysing speech data for research in neuroscience or bioacoustics.

  • Business: Leverage speech analytics to enhance customer experience, optimize AI-driven services, and understand consumer behavior.
  • Humanities and Social Sciences: Examine how speech shapes cultural identity, language policy, and social inclusion, and critically assess the ethical implications of speech technology.