photo: Martti Vainio
The Language Bank of Finland is a service for researchers using language resources. Anna Dannenberg, a postgraduate student at the University of Helsinki, describes her study on the Samples of Spoken Finnish corpus.
I am Anna Dannenberg, a postgraduate student at the University of Helsinki.
My doctoral research lies in the borderlands between general linguistics, language technology and phonetics. The topic is comparison of prosodic and syntactic structures in spoken language. The goal of the study is to discover a new viewpoint on the special grammatical characteristics of spoken language based on prosodic characteristics.
The study is based on an automated method based on Continuous Wavelet Transform (CWT) developed by professor Martti Vainio’s research group which can be used to visually model the prosodic hierarchy structure of speech. In my research, I compare these prosodic hierarchies to the syntactic structures of spoken language.
The first phase of my practical research has been comparing spoken language’s grammatical sentences to prosodic units. The first test corpus consisted of several dialect interview excerpts from the Language Bank’s Samples of Spoken Finnish corpus (SKN). The speech’s prosodic structure was modeled by applying wavelet analysis on the sound data, and syntactic sentence segmentation was produced based on the transcription separately from the sound data. The comparison of these results proved that the locations of prosodic and syntactic unit boundaries correlate strongly with each other in the speech corpus.
I presented the results of the study at the ICPhS conference in Glasgow in August 2015. After this, professor Stefan Werner and I have continued the study with a more extensive English speech corpus, but we may return to the SKN corpus as well, if at some point we want to compare the results of Finnish and English.
Information about the Samples of Spoken Finnish corpus (in Finnish)
The FIN-CLARIN consortium consists of a group of Finnish universities along with CSC – IT Center for Science and the Institute for the Languages of Finland (Kotus). FIN-CLARIN helps the researchers in Finland to use, to refine, to preserve and to share their language resources. The Language Bank of Finland is the collection of services that provides the language materials and tools for the research community.
All previously published Language Bank researcher interviews are stored in the Researcher of the Month archive.
