Jozef Vavrek

Broadcast news audio classification using SVM binary trees

Audio classification is one of the most important task in content-based analysis and can be implemented in many audio applications, such as indexing and retrieving. This paper addresses the problem of broadcast news audio classification, by support vector machine - binary tree (SVM-BT) architecture, into the five classes: pure speech, speech with music, speech with environment sound, pure music and environment sound. One of the most substantial step in creating such classification architecture is selection of an optimal feature set for each binary SVM classifier. Therefore we implement F-score feature selection algorithm, as an effective search algorithm, within a space of characteristic features that is mostly used for speech/non-speech discrimination.

Query-by-example retrieval via fast sequential dynamic time warping algorithm

We introduce a novel approach to Query-by-Example (QbE) retrieval, utilizing fundamental principles of posteriorgram-based Spoken Term Detection (STD), in this paper. Proposed approach is a kind of modification of widely used seg-mental variant of dynamic programming algorithm. Our solution represents sequential variant of DTW algorithm, employing one step forward moving strategy. Each DTW search is carried out sequentially, block by block, where each block represents squared input distance matrix, with size equal to the length of retrieved query. We also examine a way how to speed up sequential DTW algorithm without considerable loss in retrieving performance, by implementing linear time-aligned accumulated distance. The increase of detection accuracy is ensured by weighted cumulative distance score parameter. Therefore, we called this approach Weighted Fast Sequential - DTW (WFS-DTW) algorithm. A novel PCA-based silence discriminator is used along with this algorithm. Evaluation of proposed algorithm is carried out on ParDat1 corpus, using Term Weighted Value (TWV).

Audio classification utilizing a rule-based approach and the support vector machine classifier

The evaluation of two classification architectures utilizing the rule-based approach and the one-against-one support vector machine (OAO-SVM) is presented in this paper. The classification of the audio stream is carried out in two steps. At first, the rule-based speech/non-speech and music/environment sound discrimination is conducted. The set of adopted features, with a high efficiency in separation of speech and music signals, is implemented in order to find the best discriminator. Consequently, speech segments are classified into pure speech, speech with music and speech with env. sound using the OAO-SVM multi-class classification scheme. Experimental results show that the used classification architecture can decrease the classification error in comparison with OAO-SVM by using MFCC features only.

Weighted fast sequential DTW for multilingual audio Query-by-Example retrieval

This paper examines multilingual audio Query-by-Example (QbE) retrieval, utilizing the posteriorgram-based Phonetic Unit Modelling (PUM) approach and the Weighted Fast Sequential Dynamic Time Warping (WFSDTW) algorithm. The PUM approach employs phone recognizers trained on language-specific external resources in a supervised way. Thus, the information about the phonetic distribution is embedded in the process of acoustic modelling. The resulting acoustic models were also used for language-independent QbE retrieval. The improved WFSDTW algorithm was implemented in order to perform retrievals for each query (keyword) within the particular utterance file. The major interest is placed on a retrieval performance measurement of the proposed WFSDTW solution employing posteriorgram-based keyword matching with Gaussian mixture modelling (GMM). Score normalization and fusion of four different language-dependent sub-systems was carried out using a simple max-score merging strategy. The results show a certain predominance of the proposed WFSDTW solution among two other evaluated techniques, namely basic DTW and segmental DTW algorithms. Also, the combination of multiple PUM techniques together with the WFSDTW has been proved as an effective solution for the QbE task.