Abstract
This paper discusses how the transcription hurdle in dialect corpus building can be cleared. While corpus analysis has strongly gained in popularity in linguistic research, dialect corpora are still relatively scarce. This scarcity can be attributed to several factors, one of which is the challenging nature of transcribing dialects, given a lack of both orthographic norms for many dialects and speech technological tools trained on dialect data. This paper addresses the questions (i) how dialects can be transcribed efficiently and (ii) whether speech technological tools can lighten the transcription work. These questions are tackled using the Southern Dutch dialects (SDDs) as case study, for which the usefulness of automatic speech recognition (ASR), respeaking, and forced alignment is considered. Tests with these tools indicate that dialects still constitute a major speech technological challenge. In the case of the SDDs, the decision was made to use speech technology only for the word-level segmentation of the audio files, as the transcription itself could not be sped up by ASR tools. The discussion does however indicate that the usefulness of ASR and other related tools for a dialect corpus project is strongly determined by the sound quality of the dialect recordings, the availability of statistical dialect-specific models, the degree of linguistic differentiation between the dialects and the standard language, and the goals the transcripts have to serve.
Highlights
In the history of dialectological research, corpus research has long been scarce
We review a number of methods that can potentially accelerate the transcription and/or alignment process: automatic speech recognition (ASR, section Automatic speech recognition), respeaking, and forced alignment (FA)
This manual transcription is very time-consuming—with transcription speeds for our data ranging from 67 s/h for a beginning transcriber to 120 s/h for an experienced transcriber—but it is at the moment still the most efficient option, as ASR has much difficulties handling the Southern Dutch dialects (SDDs) and as such yields transcriptions with error rates that are too high to be useful for linguistic research
Summary
In the history of dialectological research, corpus research has long been scarce. Dialect atlases and dictionaries traditionally build on survey data and/or introspective data (native speaker judgments), rather than on databases of spontaneous speech samples. Considering the issues discussed above in the context of the GCND, the decision was made not to invest in ASR development, given (i) the very diverse acoustic properties of the recordings, (ii) the current lack of training data, (iii) the diversity among the SDDs and the large distance between these dialects and the standard Dutch varieties for which ASR tools have already been developed, and (iv) the high transcription accuracy needed for the further linguistic annotation and analysis of the dialect data. In the case of the GCND audio collection, which represents historical speech, transcribers often consult dialect dictionaries and studies on local customs and folklore to determine what the dialect speakers in the recordings are talking about The decision was made to stick with the original transcription protocol, as this guaranteed more consistency among transcribers
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
