Speech Technology

2020/2021

Content, progress and pedagogy of the module

The purpose of the module is to introduce the student to the theory and technology behind emerging, interactive speech systems, e.g., digital assistants such as Google Home, Amazon Echo, and Apple HomePod. This includes introductions to speech production, speech and speaker recognition, preprocessing methods, and speech synthesis. 

Learning objectives

Knowledge

Students who complete the module will be able to:

  • Explain the physiological processes of speech production
  • Explain models for approximating produced and recorded speech
  • Explain individual components of a typical interactive speech system and their relation
  • Account for the scientific foundation, and scientific problem areas, of the specialization
  • Describe the state of the art of relevant research in the specialization. 

Skills

Students who complete the module will be able to:

  • Apply methods for preprocessing of speech recordings such as beamforming and speech enhancement.
  • Apply methods and tools for speech and speaker recognition from speech recordings
  • Apply methods and tools for synthesizing speech, e.g., from text or other speech
  • Master the scientific methods and general skills associated with the specialization
  • Produce a project report according to norms of the area, apply correct terminology, document extensive command over relevant literature, communicate and discuss the research-based foundation, problem and results of the project orally, graphically and in writing in a coherent manner
  • Critically evaluate the results of the project in relation to relevant literature and established scientific methods and models, evaluate and discuss the project’s problem area in a relevant scientific context
  • Evaluate and discuss the project’s potential for further development. 

Competences

Students who complete the module will be able to:

  • Synthesize the theory, models and methods to implement an interactive speech system
  • Analyze and evaluate an interactive speech system using proper terminology and performance metrics
  • Participate in, and independently carry out, technological development and research, and apply scientific methods in solving complex problems
  • Plan, execute and manage complex research and/or development tasks, and assume a professional responsibility for independently carrying out, potentially cross-disciplinary, collaborations
  • Independently assume responsibility for own scientific development and specialization. 

Type of instruction

See the general types of instructions in §17; Structure and Contents of the Programme.

Exam

Exams

Name of examSpeech Technology
Type of exam
Oral exam based on a project
ECTS5
Permitted aids
With certain aids:
See semester description
AssessmentPassed/Not Passed
Type of gradingInternal examination
Criteria of assessmentThe criteria of assessment are stated in the Examination Policies and Procedures

Facts about the module

Danish titleTaleteknologi
Module codeMSNSMCMA3202
Module typeCourse
Duration1 semester
SemesterAutumn
ECTS5
Language of instructionEnglish
Location of the lectureCampus Aalborg
Responsible for the module

Organisation

Study BoardStudy Board of Media Technology
DepartmentDepartment of Architecture, Design and Media Technology
FacultyTechnical Faculty of IT and Design