Download now Free registration required
The rapidly increasing amount of spoken data calls for solutions to index and search this data. The classical approach consists of converting speech to word transcripts using Large Vocabulary Continuous Speech Recognition (LVCSR) tools and extending classical Information Retrieval (IR) techniques to word transcripts. Advanced word transcript search algorithms are presented by Mamou et al. However, a significant drawback of such an approach is that a search on queries containing Out-Of-Vocabulary (OOV) terms will not return any result. OOV terms are words missing in the Automatic Speech Recognition (ASR) system's vocabulary.
- Format: PDF
- Size: 112.1 KB