|
| |
|
|
Automatic Link Detection in Parts of Audiovisual Documents
Sychra, Marek ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
This paper deals with topic detection. Specifically link detection - finding similarities amongst a group of short documents according to their topic and story segmentation - finding borders between two topically different parts in a large document. The main motivation for research was practical application with the use of presentation materials from lectures at FIT (linking parts of different lectures and courses). The solution of link detection is achieved by text and word analysis, which includes learning the meaning and importance of each word. Story segmentation uses this while searching for the boundaries. Both parts of the problem (link detection, story segmentation) gave great results while testing with a standard dataset (world news reports). During evaluation of lecture processing the success rate was lower, but still good.
|
|
|
Topic Detection from Spoken Speech
Škeřík, Zdeněk ; Szőke, Igor (referee) ; Schwarz, Petr (advisor)
This thesis is about topic detection from spoken speech. The first part of the thesis deals with speech transcription to text. The thesis describes two different solutions of the topic detection - a machine learning based solution and an expert solution that composes a very precise query describing the document topic. Both methods are tested on a set of recordings and compared.
|
|
| |
|
|
Automatic Link Detection in Parts of Audiovisual Documents
Sychra, Marek ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
This paper deals with topic detection. Specifically link detection - finding similarities amongst a group of short documents according to their topic and story segmentation - finding borders between two topically different parts in a large document. The main motivation for research was practical application with the use of presentation materials from lectures at FIT (linking parts of different lectures and courses). The solution of link detection is achieved by text and word analysis, which includes learning the meaning and importance of each word. Story segmentation uses this while searching for the boundaries. Both parts of the problem (link detection, story segmentation) gave great results while testing with a standard dataset (world news reports). During evaluation of lecture processing the success rate was lower, but still good.
|
|
|
Topic Detection from Spoken Speech
Škeřík, Zdeněk ; Szőke, Igor (referee) ; Schwarz, Petr (advisor)
This thesis is about topic detection from spoken speech. The first part of the thesis deals with speech transcription to text. The thesis describes two different solutions of the topic detection - a machine learning based solution and an expert solution that composes a very precise query describing the document topic. Both methods are tested on a set of recordings and compared.
|
guest ::
