| CODE | ARI3210 | |||||||||
| TITLE | Speech Technology | |||||||||
| UM LEVEL | 03 - Years 2, 3, 4 in Modular Undergraduate Course | |||||||||
| MQF LEVEL | 6 | |||||||||
| ECTS CREDITS | 5 | |||||||||
| DEPARTMENT | Artificial Intelligence | |||||||||
| DESCRIPTION | Speech understanding and generation are fundamental to the creation of Natural Language-based interfaces. Current technologies for carrying out these tasks are now becoming viable in real-world applications. This unit will focus on these contemporary approaches, with emphasis on the following topics: - Automatic Speech Recognition, that is, the automatic decoding of speech signals obtained from speakers; - Text-to-Speech Synthesis, that is, the automatic encoding of text into fluent speech. In both cases, a diversity of approaches will be reviewed, with emphasis on contemporary statistical methods. Study-unit Aims: The unit aims to give students a practical introduction to Speech Technology, in which they will be encouraged to bring to bear their knowledge of Machine Learning to the design and implementation of systems which process speech data. In addition to a theoretical component, the unit will emphasise hands-on experience with processing speech data. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - describe the main tasks that are carried out by Speech Recognition, Speech Synthesis and other related speech processing systems; - critically evaluate the main paradigms that have been adopted in these areas to date. 2. Skills By the end of the study-unit the student will be able to: - apply theoretical concepts to practical tasks involving computational design and implementation; - appreciate the complexity of the human capacity to produce and understand speech, and the computational mechanisms that can model this capacity. Main Text/s and any supplementary readings: - T. Dutoit (1997). An introduction to text-to-speech synthesis. Dordrecht: Kluwer. - D. Jurafsky and J.H. Martin (2009). Speech and Language Processing (2nd edition). New Jersey: Prentice Hall. - T. Mitchell (1998). Machine learning. McGraw Hill. |
|||||||||
| ADDITIONAL NOTES | Pre-Requisite Study-units: ARI2203 or ICS2203 | |||||||||
| STUDY-UNIT TYPE | Lecture and Practicum | |||||||||
| METHOD OF ASSESSMENT |
|
|||||||||
| LECTURER/S | Andrea De Marco |
|||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
||||||||||