Audio segmentation of broadcast news : a hierarchical system with feature selection for the Albayzin-2010 evaluation
| Autor: | Climent Nadeu, Taras Butko |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
| Předmět: |
Audio mining
So -- Processament de dades Computer science business.industry Feature vector Speech recognition Feature extraction Speech coding Broadcasting Feature selection Pattern recognition computer.software_genre Noise Computer Science::Sound Model ocult de Markov Hierarchical control system Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic [Àrees temàtiques de la UPC] Artificial intelligence Hidden Markov models Audio signal processing business Hidden Markov model computer Albayzin 2010 |
| Zdroj: | Recercat. Dipósit de la Recerca de Catalunya instname ICASSP UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) |
| Popis: | In this paper, we present an audio segmentation system for broadcast news, and its results in the Albayzin-2010 evaluation. First of all, the Albayzin-2010 evaluation setup, developed by the authors, is presented; in particular, the database and the metric are described. The reported hierarchical HMM-GMM-based system is composed of one binary detector for each of the five considered classes (music, speech, speech over music, speech over noise and other). A fast one-pass-training feature selection technique is adapted to the audio segmentation task to improve the results and to reduce the dimensionality of the input feature vector. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|