Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. In normal cross adaptation it is assumed that useful diversity among systems exists only at acoustic level. However, complimentary features among complex LVCSR systems also manifest themselves in other layers of modelling hierarchy, e.g., subword and word level. It is thus interesting to also cross adapt language models (LM) to capture them. In this paper cross adaptation of multi-level LMs modelling both syllable and word sequences was investigated to improve LVCSR system combination. Significant error rate gains up to 6.7% rel. were obtained over ROVER and acoustic model only cross adaptation when combining 13 Chinese LVCSR subsystems used in the 2010 DARPA GALE evaluation. © 2010 ISCA.

Carta Apostólica : por la que Santa Hildegarda de Bingen, Monja Profesora de la Orden de San Benito, es proclamada Doctora de la Iglesia universal

“Luz de su pueblo y de su tiempo”: con estas palabras el beato Juan Pablo II, nuestro venerado predecesor, definió a santa Hildegarda de Bingen en 1979, en ocasión del octavo centenario de la muerte de la mística alemana. Y en verdad, sobre el horizonte de la historia esta mujer se destaca con límpida claridad, por la santidad de su vida y la originalidad de su doctrina. Como sucede en toda auténtica experiencia humana y teologal, su autoridad sobrepasa decididamente los límites de una época y de una sociedad y, a pesar de la distancia cronológica y cultural, su pensamiento se manifiesta con perenne actualidad...