|
Course Catalog 2012-2013
SGN-9206 Signal Processing Graduate Seminar II, 3-8 cr |
Additional information
Topic of the seminar will be determined and advertised in due time.
Suitable for postgraduate studies
Person responsible
Raija Lehto, Atanas Gotchev, Serkan Kiranyaz
Lessons
Study type | P1 | P2 | P3 | P4 | Summer | Implementations | Lecture times and places |
|
|
|
|
|
|
|
|
Requirements
Active participation in the seminar, seminar presentation, and final exam.
Principles and baselines related to teaching and learning
-book/article reading, slide presentations, and possible demos.
Learning outcomes
Seminar topics: signal processing and related topics, with emphasis on algorithms. After completing the seminar, students should become familiar with the seminar topic and able to exploit the methodologies learned in their own research field.
Content
Content | Core content | Complementary knowledge | Specialist knowledge |
1. | Graduate course whose topic will be announced at the beginning of the term. The core content will be described by the instructor when the scope of the seminar is defined. | Investigating topics extending the scope of the seminar. | Master the topic of the seminar and become fluent in its various research aspects. |
Evaluation criteria for the course
Attendance, presentations and exams will be used to assess performance.
Assessment scale:
Evaluation scale passed/failed will be used on the course
Study material
Type | Name | Author | ISBN | URL | Edition, availability, ... | Examination material | Language |
Book | Techniques for Noise Robustness in Automatic Speech Recognition | Tuomas Virtanen,Rita Singh,Bhiksha Raj( eds.) | Going to appear as an electronic book at the end of august 2012. Link is provided later. | Suomi |
Prerequisite relations (Requires logging in to POP)
Correspondence of content
Course | Corresponds course | Description |
|
|
Four seminars combined into one |
More precise information per implementation
Implementation | Description | Methods of instruction | Implementation |
Seminar topic is "Signal processing methods for noise-robust recognition of audio, speech and time-series analysis". Automatic speech recognition (ASR) systems are finding an increasing use in everyday life. Many of the commonplace environments where the systems are used are noisy, for example users calling up a voice search system from a busy cafeteria or a street. This can result in degraded speech recordings and adversely affect the performance of speech recognition systems. As use of ASR systems increases, knowledge of the state-of-the-art techniques to deal with such problems becomes critical to system engineers and application engineers and researchers who work with or on ASR technologies. The seminar consists of techniques used to improve the robustness of speech recognition systems to these degrading external influences. Methods presented at the seminar are very common and also suitable for signal analysis in other fields like e.g. biomedical signal processing and other similar fields. |