Understanding Linguistic Fieldwork

Meakins, Felicity; Green, Jennifer; Turpin, Myfany

doi:10.4324/9780203701294

Cited by 22 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When recording outside, the impact of wind on a recording can be minimized by using wind shields on microphones, putting up barriers to block wind, or recording in portable structures such as Green's signadome (Green, Woods, & Foley 2011); structures such as the signadome also provide shade for participants, keep out wayward dogs and children, and focus participants' attention on the recording activity at hand. For a detailed guide to planning and recording a language documentation activity in a fieldwork context, see Meakins, Green, and Turpin (2018).…”

Section: Planning For Clean Recording Audio Quality Canmentioning

confidence: 99%

Managing Transcription Data for Automatic Speech Recognition with Elpis

Foley¹,

Esch²,

San³

2022

The Open Handbook of Linguistic Data Management

View full text Add to dashboard Cite

Section: Planning For Clean Recording Audio Quality Canmentioning

confidence: 99%

Managing Transcription Data for Automatic Speech Recognition with Elpis

Foley¹,

Esch²,

San³

2022

The Open Handbook of Linguistic Data Management

View full text Add to dashboard Cite

“…Kunwinjku has limited electronic texts and lexicons, but there is a comprehensive grammar (Evans, 2003). Transcription in this context is unavoidably collaborative, with a non-speaker transcriber working with a speaker and acquiring some of the language in the process (Rice, 2011;Hanke, 2017;Meakins et al, 2018). The non-speaker transcriber can transcribe familiar words in a first pass, and later prompt a speaker to produce any unrecognized words so they can be added to the lexicon and spotted automatically.…”

Section: Local Word Discoverymentioning

confidence: 99%

Local Word Discovery for Interactive Transcription

Lane¹,

Bird²

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Human expertise and the participation of speech communities are essential factors in the success of technologies for low-resource languages. Accordingly, we propose a new computational task which is tuned to the available knowledge and interests in an Indigenous community, and which supports the construction of high quality texts and lexicons. The task is illustrated for Kunwinjku, a morphologicallycomplex Australian language. We combine a finite state implementation of a published grammar with a partial lexicon, and apply this to a noisy phone representation of the signal. We locate known lexemes in the signal and use the morphological transducer to build these out into hypothetical, morphologicallycomplex words for human validation. We show that applying a single iteration of this method results in a relative transcription density gain of 17%. Further, we find that 75% of breath groups in the test set receive at least one correct partial or full-word suggestion.

show abstract

“…We focus on discussing practical low-effort realities which are effective and include common mistakes; we do not present ideal theories, sophisticated methods, and top-notch technologies. In this sense, the present article complements textbooks such as Claire Bowern 2008;Felicity Meakins, Jennifer Green, and Myfany Turpin 2018. Unlike these sources, the current article does not focus on describing or documenting a single language from a holistic point of view (see Meakins et al 2018: 8).…”

Section: Introductionmentioning

confidence: 99%

“…For example, of the 44 languages mentioned inMeakins et al (2018), only one is a spoken language from Island SE Asia.3 Examples include local linguists associated with the Language and Culture Unit, Kupang (UBB) and the researchers from Indonesia and the Philippines involved in The Oceanic and South East Asian Navigators (OCSEAN) project, funded by the European Commission under the Horizon 2020 Marie Skłodowska-Curie Research and Innovation Staff Exchange program (MSCA-RISE-2019, Project Number 873207), see (http://www.wordsandbones.uni-tuebingen. de/ocsean/?staff-dept=member).4 The appendices to this article are also found in the version in the Zenodo Open Repository (http://doi.org/10.5281/zenodo.4041370).…”

mentioning

confidence: 99%

Practicalities of language data collection and management in and around Indonesia

Klamer

Edwards

Fricke

et al. 2021

Wacana

View full text Add to dashboard Cite

Researchers use different approaches when collecting and managing primary language materials during fieldwork. Yet it is important that this work is done in a transparent way, so that it can be used by other researchers, who might have other aims, as well as by the speaker community who might want to use or take note of the collected materials. In this article we use our research experience in language data collection in and around Indonesia in fieldwork projects of three kinds: descriptive fieldwork, linguistic surveys, and projects investigating language contact. Our aim is to provide an introductory and practical guide for students and professionals who are embarking on fieldwork in or around Indonesia. Describing practical methods of language data collection, processing, and management, our aim is to provide a guide for any research which involves the collection of language materials, including linguistic research, oral history or literature, and ethnography.

show abstract

Understanding Linguistic Fieldwork

Cited by 22 publications

References 0 publications

Managing Transcription Data for Automatic Speech Recognition with Elpis

Managing Transcription Data for Automatic Speech Recognition with Elpis

Local Word Discovery for Interactive Transcription

Practicalities of language data collection and management in and around Indonesia

Contact Info

Product

Resources

About