Comparing decoding strategies for subword-based keyword spotting in low-resourced languages

William Hartmann (1) , Viet Bac Le , Abdelkhalek Messaoudi (1) , Lori Lamel (1) , Jean-Luc Gauvain (1)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

For languages with limited training resources, out-of- vocabulary (OOV) words are a significant problem, both for transcription and keyword spotting. This paper investigates the use of subword lexical units for keyword spotting. Three strate- gies for using the sub-word units are explored: 1) converting word-based lattices to subword lattices after decoding, 2) per- forming a separate decoding for each subword type, and 3) a single decoding using all possible subword units. In these ex- periments, the best performance is achieved by carrying out a separate decoding for each subword type. Further gains are at- tained through system combination. We also find that ignor- ing word boundaries improves the detection of OOV keywords without significantly impacting in-vocabulary keyword detec- tion. Results are presented on four languages from the IARPA Babel Program (Haitian Creole, Assamese, Bengali, and Zulu).

Mots clés: keyword search; spoken term detection; OOV; sub-word lexical units; low resource LVCSR

Domaines: Informatique [cs]; Informatique et langage [cs.CL]

William Hartmann, Viet Bac Le, Abdelkhalek Messaoudi, Lori Lamel, Jean-Luc Gauvain. Comparing decoding strategies for subword-based keyword spotting in low-resourced languages. Annual Conference of the International Speech Communication Association , ISCA, Sep 2014, Singapore, Singapore. ⟨hal-01843408⟩