Title | ||
---|---|---|
A stream-based audio segmentation, classification and clustering pre-processing system for broadcast news using ANN models |
Abstract | ||
---|---|---|
Abstract This paper describes our work on the development,of a low la- tency stream-based audio pre-processing system for broadcast news using model-based techniques. It performs,speech/non- speech classification, speaker segmentation, speaker clustering, gender and background,conditions classification. As a way to increase the modelling,accuracy our algorithms make,exten- sive use of Artificial Neural Networks (ANN) thus avoiding the rough assumptions,normally made,about the audio signal dis- tribution. Experiments were conducted on the COST278 multi- lingual TV broadcast news database and compared,with current state of the art algorithms using standard evaluation tools. Ad- ditionally we investigated the impact of automatic audio pre- processing system within the recognition using a large broad- cast news,test database for the European Portuguese. These testsshow a smalldegradation,in recognition performance,when compared,with hand labelled audio segmentation. Our system is part of a prototype close-captioning system that is daily pro- cessing the main news show of two Portuguese Broadcasters. |
Year | Venue | Keywords |
---|---|---|
2005 | INTERSPEECH | artificial neural network |
DocType | Citations | PageRank |
Conference | 16 | 1.26 |
References | Authors | |
5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hugo Meinedo | 1 | 257 | 25.35 |
João Paulo Neto | 2 | 291 | 32.69 |