Programmes

BACHELOR OF SCIENCE IN SOFTWARE ENGINEERING

SENG 31573

SPEECH INTERFACES

Status : Elective Pre-requisite : SENG 21543, SENG 22582 Co-requisite : None

 

On completion of this course, the student should be able to:

  • Discuss the need for speech interfaces in software development
  • Recognize the laws and guidelines of speech interface design
  • Explain voice recognition and speech synthesis
  • Design and implement speech interfaces
  • Evaluate speech interface against usability requirements.

Introduction to speech interfaces, human factors in speech technology, cost/benefit calculation, measurement of sound, other properties of sound, how human hear sound, the verbal communication process, the structure of language, voice recognition, speech synthesis, application of speech technology: interactive voice response, medical, legal, business, handheld devices, toys and education, automobile applications.

Laws and guidelines of speech interface design: user control, human limitations, modal integrity, accommodation, linguistic clarity, aesthetic integrity, simplicity, predictability, interpretation, accuracy, technical clarity, flexibility, fulfilment, cultural property, suitable tempo, consistency, user support, precision, forgiveness, Speech guidelines: errors, feedback, conformation, user expectation, keypads and motor action, social and environmental issues, command and control, continuous speech recognition, conversation and prompting, menus, non-speech audio.

Best practices: process description, investigation, analysis, conceptual model design, detail design, implementation and evaluation, the audience for universal design, speech technology and universal design, accomplishing universal design, justification for universal design.

Lectures, practical sessions, case discussions and assignments.

End of course unit examination, case study presentations and group assignments.

  1. Weinschenk, S andBarker, D T (2011).Designing effective speech interfaces. John Wiley & Sons
  2. Pieraccini, R and Rabiner, L (2012).The Voice in the Machine: Building Computers That Understand Speech. MIT
  3. Klevans, R L and Rodman, R D (1997).Voice Recognition. Artech House Inc.

Back