Open Access. Powered by Scholars. Published by Universities.®
Language Description and Documentation Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Publication Type
Articles 1 - 3 of 3
Full-Text Articles in Language Description and Documentation
251024_Skl_Lingbing_S032_En_M_V01, Julie A. Hochgesang, Krystin Balzarini, Alexander Ivanov, Kolby Lipiz, Steve J. Saenz, Grace Shi
251024_Skl_Lingbing_S032_En_M_V01, Julie A. Hochgesang, Krystin Balzarini, Alexander Ivanov, Kolby Lipiz, Steve J. Saenz, Grace Shi
LING BING
Scott Liddell's English narrative response to the list of sample questions related to the LING BING project.
A Usage-Based Account Of Ongoing Structural Changes In Sanapaná: Grammar Sketch And Case Studies, Jens E. L. Van Gysel
A Usage-Based Account Of Ongoing Structural Changes In Sanapaná: Grammar Sketch And Case Studies, Jens E. L. Van Gysel
Linguistics ETDs
This dissertation presents three case studies on sociolinguistic variation in Sanapaná, an Enlhet-Enenlhet language spoken by around 1000 people in Paraguay. It investigates the impact of the process of language shift towards Paraguayan Guarani and Spanish that Sanapaná is undergoing. Specifically, it attempts to disentangle the effects of speakers’ multilingualism in Spanish and/or Guarani, their frequency of use of Sanapaná, and structural factors internal to Sanapaná on phonetic, morphological, and syntactic variation. It finds that Spanish/Guarani proficiency is correlated with L1-to-L2 convergence in Sanapaná vowel productions and use of different motion framing strategies, while frequency of Sanapaná usage is a …
Automatic Transcription Of Northern Prinmi Oral Art: Approaches And Challenges To Automatic Speech Recognition For Language Documentation, Connor Bechler
Automatic Transcription Of Northern Prinmi Oral Art: Approaches And Challenges To Automatic Speech Recognition For Language Documentation, Connor Bechler
Theses and Dissertations--Linguistics
One significant issue facing language documentation efforts is the transcription bottleneck: each documented recording must be transcribed and annotated, and these tasks are extremely labor intensive (Ćavar et al., 2016). Researchers have sought to accelerate these tasks with partial automation via forced alignment, natural language processing, and automatic speech recognition (ASR) (Neubig et al., 2020). Neural network—especially transformer-based—approaches have enabled large advances in ASR over the last decade. Models like XLSR-53 promise improved performance on under-resourced languages by leveraging massive data sets from many different languages (Conneau et al., 2020). This project extends these efforts to a novel context, applying …