9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Cross-Lingual Portability of MLP-Based Tandem Features - A Case Study for English and Hungarian

Lászlá Tóth (1), Joe Frankel (2), Gábor Gosztolya (1), Simon King (2)

(1) Hungarian Academy of Sciences, Hungary
(2) University of Edinburgh, UK

One promising approach for building ASR systems for lessresourced 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.

Full Paper

Bibliographic reference.  Tóth, Lászlá / Frankel, Joe / Gosztolya, Gábor / King, Simon (2008): "Cross-lingual portability of MLP-based tandem features - a case study for English and Hungarian", In INTERSPEECH-2008, 2695-2698.