Show simple item record

Proc. Interspeech 2008

dc.contributor.authorToth, Laszlo
dc.contributor.authorFrankel, Joe
dc.contributor.authorGosztolya, Gabor
dc.contributor.authorKing, Simon
dc.date.accessioned2010-10-05T11:38:56Z
dc.date.available2010-10-05T11:38:56Z
dc.date.issued2008en
dc.identifier.urihttp://hdl.handle.net/1842/3838
dc.description.abstractOne promising approach for building ASR systems for less-resourced languages is cross-lingual adaptation. Tandem ASR is particularly well suited to such adaptation, as it includes two cascaded modelling steps: feature extraction using multi-layer perceptrons (MLPs), followed by modelling using a standard HMM. The language-specific tuning can be performed by adjusting the HMM only, leaving the MLP untouched. Here we examine the portability of feature extractor MLPs between an Indo-European (English) and a Finno-Ugric (Hungarian) language. We present experiments which use both conventional phone-posterior and articulatory feature (AF) detector MLPs, both trained on a much larger quantity of (English) data than the monolingual (Hungarian) system. We find that the cross-lingual configurations achieve similar performance to the monolingual system, and that, interestingly, the AF detectors lead to slightly worse performance, despite the expectation that they should be more language-independent than phone-based MLPs. However, the cross-lingual system outperforms all other configurations when the English phone MLP is adapted on the Hungarian data.en
dc.titleCross-lingual Portability of MLP-Based Tandem Features -- A Case Study for English and Hungarianen
dc.typeConference Paperen
rps.titleProc. Interspeech 2008en
dc.extent.noOfPages2695-2698en
dc.date.updated2010-10-05T11:38:56Z
dc.date.openingDate2008-09


Files in this item

This item appears in the following Collection(s)

Show simple item record