Conference Publications

Permanent URI for this collection

http://hdl.handle.net/10204/11486

Browse

Browsing Conference Publications by Subject "10th Annual Conference of the International Speech Communication Association"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Language modeling for what-with-where on GOOG-411
    (International Speech Communication Association, 2009-09) Van Heerden, C; Schalkwyk, J; Strope, B
    This paper describes the language modelling (LM) architectures and recognition experiments that enabled support of 'what-with-where' queries on GOOG-411. First the paper compares accuracy trade-offs between a single national business LM for business queries and using many small models adapted for particular cities. Experimental evaluations show that both approaches lead to comparable overall accuracy. Differences in the distributions of errors also lead to improvements from a simple combination. The researchers then optimize variants of the national business LM in the context of combined business and location queries from the web, and finally evaluate these models on a recognition test from the recently fielded ’what-with-where’ system.
  • Thumbnail Image
    Item
    Pronunciation dictionary development in resource-scarce environments
    (International Speech Communication Association, 2009-09) Davel, M; Martirosian, O
    The deployment of speech technology systems in the developing world is often hampered by the lack of appropriate linguistic resources. A suitable pronunciation dictionary is one such resource that can be difficult to obtain for lesser-resourced languages. Researchers design a process for the development of pronunciation dictionaries in resource-scarce environments, and apply this to the development of pronunciation dictionaries for ten of the official languages of South Africa. The paper defines the semiautomated development and verification process in detail and discusses practicalities, outcomes and lessons learnt. It further analyse the accuracy of the developed dictionaries and demonstrate how the distribution of rules generated from the dictionaries provides insight into the inherent predictability of the languages studied.