Incorporating knowledge sources into statistical speech recognition

Incorporating Knowledge Sources into Statistical Speech Recognition addressesthe problem of developing efficient automatic speech recognition (ASR) systems, which maintain a balance between utilizing a wide knowledge of speech variability, while keeping the training / recognition effort feasible and improvingspeech recognition performance. The book provides an efficient general framework to incorporate additional knowledge sources into state-of-the-art statistical ASR systems. It can be applied to many existing ASR problems with their respective model-based likelihood functions in flexible ways. Provides an efficient general framework to incorporate additional knowledge sources into state-of-the-art statistical ASR systems Demonstrates applications to existing ASR problems with their respective model-based likelihood functions in flexible ways INDICE: Introduction and Book Overview.- Statistical Speech Recognition.- Graphical Framework to Incorporate Knowledge Sources.- Speech Recognition Using GFIKS.- Conclusions and Future Directions.

• ISBN: 978-0-387-85829-6
• Editorial: Springer
• Encuadernacion: Cartoné
• Páginas: 196
• Fecha Publicación: 01/03/2009
• Nº Volúmenes: 1
• Idioma: Inglés