Speech Processing (Hons) (LASC10061)
Language Sciences and Linguistics
Normal Year Taken
Delivery Session Year
Visiting student must have completed at least 3 Linguistics/Language Sciences courses at grade B or above. We will only consider University/College level courses. **The Language Sciences courses offered at the University of Edinburgh are extremely intensive and visiting students have struggled with these courses in previous years. Students are expected to have a strong background in Linguistics as an academic discipline; courses that are part of a Modern Foreign Languages degree may not provide students with an adequate background**
A foundation course in speech processing for students of linguistics, informatics, and related subjects. Enrolments for students outwith Philosophy, Psychology and Language Sciences must be approved by the Course Organiser.
In this course, students investigate the fundamentals of speech signal processing, text-to-speech systems, and automatic speech recognition. This is a fast-paced course which draws on topics from linguistics, informatics, and engineering, including the following: **Foundations in phonetics and signal processing: sound and waveforms, the connection between speech acoustics and speech articulation, time versus frequency representations of speech, the Discrete Fourier Transform and frequency spectrums, the source-filter model of speech. **Text-to-speech synthesis: components of a concatenative text-to-speech synthesiser, introduction to automatic text analysis, waveform generation and speech modification methods. **Automatic Speech recognition: components of a typical speech recognition system, speech feature representations, measuring similarity in speech using probabilistic methods, Hidden Markov Models (HMMs) for ASR, training and testing probabilistic models with speech data. The course is delivered as a combination of lectures, an online forum, videos, readings, and practical exercises in the lab. The course work will be based on lab exercises where students investigate an existing text-to-speech system, and build a simple automatic speech recognition system. Students deciding whether to take this course should visit https://speech.zone/courses/speech-processing/ where much of the course material can be found.
Written Exam 0%, Coursework 100%, Practical Exam 0%
All course information obtained from this visiting student course finder should be regarded as provisional. We cannot guarantee that places will be available for any particular course. For more information, please see the visiting student disclaimer: