Teaching


    Introduction to Speech Technology

I teach a course in Introduction to Speech Technology which is part of the Professional MS in Computational Linguistics.

Speech is our most natural form of communication. With the power of modern computing devices, technology advancements and adaptive designs, speech technology has become a viable interface for millions of users every day serving a wide range of scenarios.

The goal of this course is to give an introduction to the key concepts and components of speech technology. We will design and build some of the underlying building blocks including your own speech recognizer and discuss how speech applications fit in today's world.

Topics include:
  • The mechanics of current speech technologies: automatic speech recognition (ASR), text-to-speech (TTS) and speaker verification and identification (SVI) with particular focus on ASR
  • Hands-on experience with the software development process through a review of techniques for successful implementation of speech technology components
  • Application design with a review of challenges in solving real life needs for e.g. people on the go and users with disabilities
  • Human-to-human speech communication vs. speech technology
  • Speech technology research, the innovation process and the future



    MS Student theses and projects

  • Maria Alexandropoulou: Agreement/Disagreement detection and the role of linguistic coordination and conversational features, 2014
  • Anthony Gentile: Sentence structure in domain adaptation for sentiment classification, 2013
  • Stella Podgornik: Automatic detection of language levels in L2 English learners, 2013
  • Ka Yee Lun: Feature extraction for Cantonese ASR, 2012
  • Andrew Freeman: Automatic diacritic recovery and dialect recognition of Yemeni Arabic, 2010
  • Anya Smirnova: Automatic spoken language identification, 2010




Back to the top

Professional MS in Computational Linguistics  |  Department of Linguistics  |  University of Washington