Workshop Program

All times are Hawaii Standard Time (HST), GMT-10.

March 5

Welcome and Introduction
Special Session: Justice through Technology

Each Special Session talk is 20 minutes, followed by 10 minutes for questions
10:40-11:10Integrating text-to-speech in an online language learning platformChristopher Hammerly, Chad Quinn[Talk]
11:10-11:40Promoting inclusion and improving corpus quality through software trainingKelsey Neely, Vera Ferreira, Mandana Seyfeddinipur[Talk]
11:40-12:10Implementing OCAP, CARE and FAIR in managing digital language dataDante Cerron, Julia Chu[Talk]
12:10-12:40Community Developed Voice AI XRMichael Running Wolf
12:40-13:30Round table discussion, with discussant Daisy RosenblumDiscussion: All presenters from the Special Session, Daisy Rosenblum, discussant
General Session Day 1

Each General Session talk is a 5-minute summary, followed by 10 minutes questions
16:00-16:15User-Centric Evaluation of OCR Systems for Kwak'walaShruti Rijhwani, Daisy Rosenblum, Michayla King, Antonios Anastasopoulos, Graham Neubig[PDF]
16:15-16:30Towards a finite-state morphological analyser for San Mateo HuaveFrancis M. Tyers, Samuel Herrera Castro[PDF]
16:30-16:45A morphological analyzer for Huasteca NahuatlAna Tona, Guillaume Thomas, Ewan Dunbar[PDF] [Talk]
17:00-17:15LSDT: a Dependency Treebank of Lombard SintiMarco Forlano, Luca Brigada Villa[PDF] [Talk]
17:15-17:30Towards Universal Dependencies in Cook Islands MāoriSarah Karnes, Rolando Coto, Sally Akevai Nicholas[PDF] [Talk]

March 6

General Session Day 2

Each General Session talk is a 5-minute summary, followed by 10 minutes questions
9:00-9:15Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptionsNay San, Martijn Bartelds, Blaine Billings, Ella de Falco, Hendi Feriza, Johan Safri, Wawan Sahrozi, Ben Foley, Bradley McDonnell, Dan Jurafsky[PDF] [Talk]
9:15-9:30Studying the impact of language model size for low-resource ASRZoey Liu, Justin Spence, Emily Prud'Hommeaux[PDF]
9:30-9:45Speech-to-text recognition for multilingual spoken data in language documentationLorena Martín Rodríguez, Christopher Cox[PDF] [Talk]
10:00-10:15FileLingR: An R Script validation tool for depositors and users of digital language collectionsIrene Yi, Claire Bowern[PDF] [Talk]
10:15-10:30Investigating Speaker Diarization of Endangered Language DataGina-Anne Levow[PDF] [Talk]
10:30-10:45From Raw Data to Acoustic Analysis: A Roadmap for Acquaviva CollecroceSimon Gonzalez[PDF] [Talk]
Midday Break
General Session Day 2

Each General Session talk is a 5-minute summary, followed by 10 minutes questions
11:45-12:00A Survey of Computational Infrastructure to Help Preserve and Revitalize BodwéwadmimwenRobert Lewis[PDF] [Talk]
12:00-12:15Auto-Transcription of Endangered Sign Languages Using Object Detection and Colocalization AnalysisOlivia Waring[PDF] [Talk]
12:30-12:45Challenges and Issue of Gender Bias in Under-Represented Languages: An Empirical Study on Inuktitut-English NMTNgoc Tan Le, Oussama Hansal, Fatiha Sadat[PDF] [Talk]
12:45-13:00A text-to-speech synthesis system for Border Lakes OjibweChristopher Hammerly, Sonja Fougère, Giancarlo Sierra, Scott Parkhill, Harrison Porteous, Chad Quinn[PDF] [Talk]
13:00-13:15Text normalization for low-resource languages: the case of LigurianStefano Lusito, Edoardo Ferrante, Jean Maillard[PDF] [Talk]
13:30-13:45Morphological Data Generation from FLExShengyu Liao, Sarah Moeller, Beth Bryson[PDF] [Talk]
13:45-14:00Using LARA to rescue a legacy Pitjantjatjara courseManny Rayner, Sasha Wilmoth[PDF] [Talk]
14:00-14:15Applications of classification trees for endangered language description: Finite verb morphology in Kolyma YukaghirAlbert Ventayol-Boada[PDF] [Talk]
Closing Remarks from SIGEL President
SIGEL Business Meeting (Open to membership)