Attention shift decoding for conversational speech recognition

Abstract-Most speech recognizers do not differentiate between reliable and unreliable portions of the speech signal during search. As a result, most of the search effort is concentrated in unreliable areas. Island-driven search addresses this problem by first identifying reliable islands and directing the search out from these islands towards unreliable gaps. In this paper, we develop a technique to detect islands from knowledge of hypothesized broad phonetic classes (BPCs). Using this island/gap knowledge, we explore a method to prune the search space to limit computational effort in unreliable areas. In addition, we also investigate scoring less detailed BPC models in gap regions and more detailed phonetic models in islands. Experiments on both small and large scale vocabulary tasks indicate that our islanddriven search strategy results in an improvement in recognition accuracy and computation time.

show abstract

Cognitive Multimodal Processing

Potamianos

2014

Proceedings of the 2014 Workshop on Roadmapping the Future of Multimodal Interaction Research Including Business Opportunities

View full text Add to dashboard Cite

Attention shift decoding for conversational speech recognition

Cited by 4 publications

References 7 publications

Using knowledge on word-islands to improve the performance of spoken dialogue systems

Using knowledge on word-islands to improve the performance of spoken dialogue systems

Island-driven search using broad phonetic classes

Cognitive Multimodal Processing

Contact Info

Product

Resources

About