Voice Search of Structured Media Data
- Young-In Song ,
- Ye-Yi Wang ,
- Y. C. Ju ,
- Mike Seltzer ,
- Ivan Tashev ,
- Alex Acero
International Conference on Acoustics, Speech and Signal Processing |
Published by Institute of Electrical and Electornic Engineers, Inc.
This paper addresses the problem of using unstructured queries to search a structured database in voice search applications. By incorporating structural information in music metadata, the end-to-end search error has been reduced by 15% on text queries and up to 11% on spoken queries. Based on that, an HMM sequential rescoring model has reduced the error rate by 28% on text queries and up to 23% on spoken queries compared to the baseline system. Furthermore, a phonetic similarity model has been introduced to compensate speech recognition errors, which has improved the end-to-end search accuracy consistently across different levels of speech recognition accuracy.