|
Lecturer(s)
|
-
Pražák Aleš, Ing. Ph.D.
-
Radová Vlasta, Doc. Dr. Ing.
|
|
Course content
|
Process of speech production by humans, phonetics. Principle of automatic speech recognition systems, acoustic model, language model. Areas, where automatic speech recognition systems can be used. Drawbacks of speech recognition systems. Task of a shadow speaker in automatic speech recognition systems. Systems for shadow speaker training. Introduction into usage of automatic speech recognition systems. Shadow speaker training.
|
|
Learning activities and teaching methods
|
Lecture with practical applications, Individual study, Lecture, Lecture with visual aids, Practicum
- Contact hours
- 39 hours per semester
- Preparation for an examination (30-60)
- 30 hours per semester
- Practical training (number of hours)
- 35 hours per semester
|
| prerequisite |
|---|
| Knowledge |
|---|
| No special preconditions are required. |
| Skills |
|---|
| to use a computer |
| learning outcomes |
|---|
| Knowledge |
|---|
| to understand the principle of automatic speech recognition systems |
| to describe characteristics (namely drawbacks) of speech recognition systems |
| to explain the task of shadow speakers in automatic speech recognition systems |
| Skills |
|---|
| to use the speech recognition systems |
| to demonstrate the task of shadow speakers in automatic speech recognition systems |
| teaching methods |
|---|
| Knowledge |
|---|
| Lecture |
| Lecture with visual aids |
| Practicum |
| Individual study |
| Interactive lecture |
| assessment methods |
|---|
| Combined exam |
| Skills demonstration during practicum |
| Continuous assessment |
|
Recommended literature
|
-
Psutka, Josef. Komunikace s počítačem mluvenou řečí. Praha : Academia, 1995. ISBN 80-200-0203-0.
-
Psutka, Josef. Mluvíme s počítačem česky. Praha : Academia, 2006. ISBN 80-200-1309-1.
|