This course on Multilingual NLP focuses on speech processing. The learning outcomes include understanding speech, speech applications, databases, and the speech hierarchy. The course covers skills such as speech waveform analysis, speech coding, ASR, TTS, speech translation, privacy in speech, and speech enhancement. The teaching method involves lectures and examples. The intended audience for this course is individuals interested in multilingual natural language processing and speech technology.
Overview
Syllabus
Intro
What is speech???
Speech waveform
What kind of information does speech sound contain?
Speech coding
Automatic Speech Recognition (ASR)
Speech Synthesis (TTS: Text to Speech)
Speech Translation
Privacy in speech
Speech enhancement Several types of problems
Speech variations Speaking styles and environments
Read speech examples
Spontaneous speech
Where we found the speech data?
Taught by
Graham Neubig
