Comparative analysis between HMM and GMM-UBM methods: - Martins, Ramon Mayor
18,99 €
inkl. MwSt.

Versandfertig in 1-2 Wochen
payback
9 °P sammeln
  • Broschiertes Buch

This research addresses ways to minimize the high error rate in speech recognition systems trained with adult speakers and tested with child speakers. The GMM-UBM method is used as an alternative to the HMM method in the search for the optimal scaling factor (¿-optimal) for child voiceovers when using the speaker standardization technique. The normalization technique adopted is the VTLN, which normalizes the vocal tract of different child speakers through the frequency scaling of the honey filter bank. In the evaluation of this technique, we also looked for the amount of optimal mixtures that improve the performance of the system.…mehr

Andere Kunden interessierten sich auch für
Produktbeschreibung
This research addresses ways to minimize the high error rate in speech recognition systems trained with adult speakers and tested with child speakers. The GMM-UBM method is used as an alternative to the HMM method in the search for the optimal scaling factor (¿-optimal) for child voiceovers when using the speaker standardization technique. The normalization technique adopted is the VTLN, which normalizes the vocal tract of different child speakers through the frequency scaling of the honey filter bank. In the evaluation of this technique, we also looked for the amount of optimal mixtures that improve the performance of the system.
Autorenporträt
Master in Telecommunicatie door het Nationaal Instituut voor Telecommunicatie - INATEL (2014). Elektrotechnisch ingenieur met de nadruk op Telematica, aan de Universiteit van Zuid-Santa Catarina - UNISUL. Momenteel bekleedt hij de functie van hoogleraar Basisonderwijs, Technisch en Technologisch, op het gebied van Telecommunicatie, aan het Federale Instituut van Santa Catarina, São Jose.