Announcements || Academic Integrity || Description
  Resources || Requirements || Syllabus || Readings

Description:

This course introduces students to research in spoken language in computational linguistics, aka natural language processing (NLP). We will examine approaches to the analysis of the speech signal of particular interest to NLP research, look at several speech technologies in some detail, including approaches to recognizing and to generating speech, and consider several important application areas for these technologies, including spoken dialogue systems and speech data mining. There are no formal prerequisites for the course (i.e. no knowledge of speech or signal processing is assumed) but some knowledge of/serious interest in NLP is assumed. Format for the class will be lecture and discussion. NB: This course can be counted as a PhD elective in Advanced AI.

Readings:

Acoustic & Auditory Phonetics by Keith Johnson  is available from Papyrus.  Speech and Language Processing by Jurafsky and Martin will be a useful reference for those with no formal background in NLP. The early chapters of one of the following paperbacks, The Speech Chain by Peter Denes and Elliot Pinson (on reserve in Psychology Library), Elements of Acoustic Phonetics by Peter Ladefoged will also be useful. Used copies of all these should be available in local bookstores, as well as from Amazon and other online providers. Most course readings will be available either on the web or in-class handouts. NB: '*' means that the reading is optional.

Requirements:

Class participation and a term project. Class participation will include a) bringing 3 discussion questions to class each week, based on the readings; and b) helping with one class during the semester. The project (done alone or in collaboration) on one of the topics coverered in the course or some other topic in spoken language will be defined by each class participant in consultation with the professor. These projects will involve a) a project description; b) periodic project reports on progress; c) a class presentation of project results; and d) delivery of the final project. Project formats may include literature reviews, data collection and analysis, experiments, and/or systems or system components.

Academic Integrity:

Copying or paraphrasing someone's work (code included), or permitting your own work to be copied or paraphrased, even if only in part, is not allowed, and will result in an automatic grade of 0 for the entire assignment or exam in which the copying or paraphrasing was done. Your grade should reflect your own work. If you believe you are going to have trouble completing an assignment, please talk to the professor in advance of the due date.

Announcements:

Resources:

Help using xwaves
Help using ToBI
Getting wavesurfer

Text-to-Song synthesis!

Syllabus:

Announcements || Academic Integrity || Description
Links to Resources || Requirements || Syllabus || Text || Thanks