|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (oponent) ; Kesiraju, Santosh (vedoucí práce)
This thesis deals with the problems of language recognition and topic classification, using TED-LIUM corpus to train both the ASR and classification models. The ASR system is built using the Kaldi toolkit, achieving the WER of 16.6%. The classification problem is addressed using linear classification methods, specifically Multinomial Naive Bayes and Linear Support Vector Machines, the latter method achieving higher topic classification accuracy.
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (oponent) ; Kesiraju, Santosh (vedoucí práce)
This thesis deals with the problems of language recognition and topic classification, using TED-LIUM corpus to train both the ASR and classification models. The ASR system is built using the Kaldi toolkit, achieving the WER of 16.6\%. The classification problem is addressed using linear classification methods, specifically Multinomial Naive Bayes and Linear Support Vector Machines, the latter method achieving higher topic classification accuracy.
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (oponent) ; Kesiraju, Santosh (vedoucí práce)
This thesis deals with the problems of language recognition and topic classification, using TED-LIUM corpus to train both the ASR and classification models. The ASR system is built using the Kaldi toolkit, achieving the WER of 16.6%. The classification problem is addressed using linear classification methods, specifically Multinomial Naive Bayes and Linear Support Vector Machines, the latter method achieving higher topic classification accuracy.
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (oponent) ; Kesiraju, Santosh (vedoucí práce)
This thesis deals with the problems of language recognition and topic classification, using TED-LIUM corpus to train both the ASR and classification models. The ASR system is built using the Kaldi toolkit, achieving the WER of 16.6\%. The classification problem is addressed using linear classification methods, specifically Multinomial Naive Bayes and Linear Support Vector Machines, the latter method achieving higher topic classification accuracy.
|