The 2011 KIT QUAERO Speech-to-Text System for Spanish
Abstract:
This paper describes our current Spanish speech-to-text (STT) system with which we participated in the 2011 Quaero STT evaluation that is being developed within the Quaero program. The system consists of 4 separate subsystems, as well as the standard MFCC and MVDR phoneme based subsystems we included a both a phoneme and grapheme based bottleneck subsystem. We carefully evaluate the performance of each subsystem. After including several new techniques we were able to reduce the WER by over 30% from 20.79% to 14.53%.
| Zugehörige Institution(en) am KIT | Fakultät für Informatik – Institut für Anthropomatik (IFA) Institut für Anthropomatik und Robotik (IAR) |
| Publikationstyp | Proceedingsbeitrag |
| Publikationsjahr | 2011 |
| Sprache | Englisch |
| Identifikator | KITopen-ID: 1000030224 |
| Erschienen in | International Workshop on Spoken Language Translation (IWSLT 2011), San Francisco, California, USA, December 8-9 2011 |
| Veranstaltung | International Workshop on Spoken Language Translation (IWSLT 2011), San Francisco, CA, USA, 08.12.2011 – 09.12.2011 |
| Verlag | ISCA |
| Seiten | 199-205 |
| Externe Relationen | Siehe auch Siehe auch |