Prediction of three articulatory categories in vocal sound imitations using models for auditory receptive fields

QC 20181003
Vocal sound imitations provide a new challenge for understanding the coupling between articulatory mechanisms and the resulting audio. In this study, we have modeled the classification of three articulatory categories, phonation, supraglottal myoelastic vibrations, and turbulence from audio recordings. Two data sets were assembled, consisting of different vocal imitations by four professional imitators and four non-professional speakers in two different experiments. The audio data were manually annotated by two experienced phoneticians using a detailed articulatory description scheme. A separate set of audio features was developed specifically for each category using both time-domain and spectral methods. For all time-frequency transformations, and for some secondary processing, the recently developed Auditory Receptive Fields Toolbox was used. Three different machine learning methods were applied for predicting the final articulatory categories. The result with the best generalization was found using an ensemble of multilayer perceptrons. The cross-validated classification accuracy was 96.8 % for phonation, 90.8 % for supraglottal myoelastic vibrations, and 89.0 % for turbulence using all the 84 developed features. A final feature reduction to 22 features yielded similar results.

Lindeberg, Tony,Professor,1964-KTH,Beräkningsvetenskap och beräkningsteknik (CST)(Swepub:kth)u1ht8xqq (author)
Hellwagner, MartinKTH,Tal, musik och hörsel, TMH(Swepub:kth)u1jzttcs (author)
Helgason, PéturKTH,Tal, musik och hörsel, TMH(Swepub:kth)u1yyj4gs (author)
Salomão, Gláucia Laís,PhDStockholms universitet,KTH,Tal, musik och hörsel, TMH,Avdelningen för fonetik,SUBIC – Centrum för hjärnavbildning vid Stockholms universitet,Speech, Music and Hearing, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology 1 , Lindstedtsvägen 24, 10044 Stockholm, Sweden(Swepub:su)glsa5764 (author)
Elowsson, AndersKTH,Tal, musik och hörsel, TMH(Swepub:kth)u1m285z5 (author)
Lemaitre, GuillaumeInstitute for Research and Coordination in Acoustics and Music, Paris, France (author)
Ternström, Sten,1956-KTH,Tal, musik och hörsel, TMH(Swepub:kth)u1bc9kv8 (author)
KTHTal, musik och hörsel, TMH (creator_code:org_t)

In:Journal of the Acoustical Society of America: Acoustical Society of America (ASA)144:3, s. 1467-14830001-49661520-8524

By the author/editor: Friberg, Anders, ...; Lindeberg, Tony, ...; Hellwagner, Mart ...; Helgason, Pétur; Salomão, Gláucia ...; Elowsson, Anders; show more...; Lemaitre, Guilla ...; Ternström, Sten, ...; show less...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Signal Processin ...

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Mechanical Engin ...; and Fluid Mechanics ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.