Automatic Classification of Regular vs. Irregular Phonation Types

Bőhm, Tamás M.; Both, Z.; Németh, György

doi:10.1007/978-3-642-11509-7_6

Cited by 5 publications

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One major difficulty with studying creaky voice, and indeed voice quality in general, is the problem of reconciling the variation in the terminology used in the literature. Many studies use the terms irregular phonation (Slifka, 2006;Surana and Slifka, 2006a;Vishnubhotla and Espy-Wilson, 2006;Böhm et al, 2010) or glottalisation (Dilley et al, 1996;Redi and Shattuck-Hufnagel, 2001). However, both these terms are rather broad and indeed cover other classes of phonation (or laryngeal activity) aside from what we consider as creaky voice.…”

Section: Terminologymentioning

confidence: 99%

Data-driven detection and analysis of the patterns of creaky voice

Drugman

Kane

Gobl

2014

Computer Speech & Language

View full text Add to dashboard Buy / Rent full text

This paper investigates the temporal excitation patterns of creaky voice. Creaky voice is a voice quality frequently used as a phrase-boundary marker, but also as a means of portraying attitude, affective states and even social status. Consequently, the automatic detection and modelling of creaky voice may have implications for speech technology applications. The acoustic characteristics of creaky voice are, however, rather distinct from modal phonation. Further, several acoustic patterns can bring about the perception of creaky voice, thereby complicating the strategies used for its automatic detection, analysis and modelling. The present study is carried out using a variety of languages, speakers, and on both read and conversational data and involves a mutual information-based assessment of the various acoustic features proposed in the literature for detecting creaky voice. These features are then exploited in classification experiments where we achieve an appreciable improvement in detection accuracy compared to the state of the art. Both experiments clearly highlight the presence of several creaky patterns. A subsequent qualitative and quantitative analysis of the identified patterns is provided, which reveals a considerable speaker-dependent variability in the usage of these creaky patterns. We also investigate how creaky voice detection systems perform across creaky patterns.

show abstract

Section: Terminologymentioning

confidence: 99%

Data-driven detection and analysis of the patterns of creaky voice

Drugman

Kane

Gobl

2014

Computer Speech & Language

View full text Add to dashboard Buy / Rent full text

show abstract

“…Some studies describe automatic detection of 'irregular phonation' (see e.g., Böhm et al, 2010;Surana and Slifka, 2006a;Vishnubhotla and Espy-Wilson, 2006), a class within which creak is contained. For instance in Böhm et al (2010) the authors derive six acoustic parameters and use them as input to a support vector machine (SVM) based classification system. Their method involved using acoustic measurements from previous studies (i.e.…”

Section: State-of-the-artmentioning

confidence: 99%