Induced Inflection-Set Keyword Search in Speech
This provides a domain-specific method for speech search, though it appears incremental as it builds on existing inflection generation approaches.
The paper tackles the problem of searching for lexeme-sets in speech by using their inflectional variants, showing how performance changes with the number of hypothesized inflections and the importance of curated inflectional paradigms in the search pipeline.
We investigate the problem of searching for a lexeme-set in speech by searching for its inflectional variants. Experimental results indicate how lexeme-set search performance changes with the number of hypothesized inflections, while ablation experiments highlight the relative importance of different components in the lexeme-set search pipeline and the value of using curated inflectional paradigms. We provide a recipe and evaluation set for the community to use as an extrinsic measure of the performance of inflection generation approaches.