This paper provides a thorough description of a methodology which leads to high accuracy as regards automatic analysis of broadcast audio. The main objective is to find a feature set for efficient speech/music discrimination while keeping the number of its dimensions as small as possible. Three groups of parameters based on Mel-scale filterbank, MPEG-7 standard and wavelet decomposition are examined in detail. We annotated on-line radio recordings characterized by great diversity, for building probabilistic models and testing four frameworks. The proposed approach utilizes wavelets and MPEG-7 ASP descriptor for modeling speech and music respectively, and results to 98.5 % average recognition rate
A comparative study in automatic recognition of broadcast audio / S. Ntalampiras, N. Fakotakis (INTERSPEECH). - In: Proceedings of the Annual Conference of the International Speech Communication Association[s.l] : ISCA, 2008. - ISBN 9781615673780. - pp. 2498-2501 (( Intervento presentato al 9. convegno INTERSPEECH tenutosi a Brisbane nel 2008.
A comparative study in automatic recognition of broadcast audio
S. Ntalampiras;
2008
Abstract
This paper provides a thorough description of a methodology which leads to high accuracy as regards automatic analysis of broadcast audio. The main objective is to find a feature set for efficient speech/music discrimination while keeping the number of its dimensions as small as possible. Three groups of parameters based on Mel-scale filterbank, MPEG-7 standard and wavelet decomposition are examined in detail. We annotated on-line radio recordings characterized by great diversity, for building probabilistic models and testing four frameworks. The proposed approach utilizes wavelets and MPEG-7 ASP descriptor for modeling speech and music respectively, and results to 98.5 % average recognition rate
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
