%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:14:19 PM

@ARTICLE{Cernak_CSL_2016,
         author = {Cernak, Milos and Be{\v n}u{\v s}, {\v S}tefan and Lazaridis, Alexandros},
         editor = {ten Bosch, Louis},
       projects = {Idiap, SIWIS},
          title = {Speech vocoding for laboratory phonology},
        journal = {Computer Speech and Language},
           year = {2016},
       crossref = {Cernak_Idiap-RR-07-2015},
            pdf = {https://publications.idiap.ch/attachments/papers/2016/Cernak_CSL_2016.pdf}
}



crossreferenced publications: 
@TECHREPORT{Cernak_Idiap-RR-07-2015,
         author = {Cernak, Milos and Be{\v n}u{\v s}, {\v S}tefan and Lazaridis, Alexandros},
       keywords = {laboratory phonology, parametric speech synthesis, Phonological speech representation},
       projects = {Idiap},
          month = {5},
          title = {Speech vocoding for laboratory phonology},
           type = {Idiap-RR},
         number = {Idiap-RR-07-2015},
           year = {2015},
    institution = {Idiap},
       abstract = {In this paper, we propose a platform based on phonological speech vocoding for examining relations
between phonology and speech processing, and in broader terms, between the abstract and physical
structures of speech signal. The goal of this paper is to go a step further towards bridging both fields
and contributing to the program of Laboratory Phonology. We show two application examples for the
laboratory phonology: a comparison of the phonological systems and an experimental phonological
parametric text-to-speech (TTS) system. The following three phonological systems are considered in
this work: (i) Government Phonology (GP) features, (ii) the Sound Pattern of English (SPE) features,
and (iii) the extended SPE (eSPE) features. Comparing GP- and eSPE-based vocoded speech, we con-
clude that eSPE achieves slightly better results than the other two systems. However, GP – the most
compact phonological speech representation – performs comparably to the systems with higher number
of phonological classes. The parametric TTS based on phonological speech representation, and trained
from an unlabelled audio book in an unsupervised manner, achieves promising results.
We envision that the presented approach paves the way for researchers in both fields to form mean-
ingful hypotheses that are explicitly testable using the concepts developed and exemplified in this paper.
Laboratory phonologists might test the applied concepts of their theoretical models and speech pro-
cessing community may be suggesting tests for the potential of advancing the performance of current
state-of-the-art applications using the concepts developed for the theoretical phonological models.},
            pdf = {https://publications.idiap.ch/attachments/reports/2015/Cernak_Idiap-RR-07-2015.pdf}
}