%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 12:29:47 PM

@INPROCEEDINGS{Lazaridis_IWSLT_2016,
         author = {Lazaridis, Alexandros and Himawan, Ivan and Motlicek, Petr and Mporas, Iosif and Garner, Philip N.},
       projects = {SUMMA, MALORCA},
          month = dec,
          title = {Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages},
      booktitle = {Proceedings of the International Workshop on Spoken Language Translation},
           year = {2016},
       location = {Seattle, WA, USA},
       abstract = {The multi-level adaptive networks (MLAN) technique is a
cross-lingual adaptation framework where a bottleneck (BN)
layer in a deep neural network (DNN) trained in a source lan-
guage is used for producing BN features to be exploited in a
second DNN in a target language. We investigate how the
correlation (in the sense of phonetic similarity) of the source
and target languages and the amount of data of the source
language affect the efficiency of the MLAN schemes. We
experiment with three different scenarios using, i) French,
as a source language uncorrelated to the target language, ii)
Ukrainian, as a source language correlated to the target one
and finally iii) English as a source language uncorrelated to
the target language using a relatively large amount of data in
respect to the other two scenarios. In all cases Russian is used
as target language. GLOBALPHONE data is used, except
for English, where a mixture of LIBRISPEECH, TEDLIUM
and AMIDA is available. The results have shown that both
of these two factors are important for the MLAN schemes.
Specifically, on the one hand, when a modest amount of
data from the source language is used, the correlation of
the source and target languages is very important. On the
other hand, the correlation of the two languages seems to be
less important when a relatively large amount of data, from
the source language, is used. The best performance in word
error rate (WER), was achieved when the English language
was used as the source one in the multi-task MLAN scheme,
achieving a relative improvement of 9.4\% in respect to the
baseline DNN model.},
            pdf = {https://publications.idiap.ch/attachments/papers/2016/Lazaridis_IWSLT_2016.pdf}
}