Скачать с ютуб Mobilising the Archive:Training Modern Speech Technology Modelswith Digitalised Fieldwork Recordings в хорошем качестве

Mobilising the Archive:Training Modern Speech Technology Modelswith Digitalised Fieldwork Recordings

"Mobilising the Archive: Training Modern Speech Technology Models with Digitalised Fieldwork Recordings" Presented by William N. Havard, Benjamin Lecouteux and Emmanuel Schang at the Language Documentation and Archiving Conference, Berlin & Online, 4-6 Sept, 2024 #lda2024 Over the years, community members and linguists have recorded speakers and peers in the field to formally study their languages and write grammars, and to preserve cultural knowledge. Up to now, most of the gathered recordings are archived and remain untranscribed. They are therefore impossible to index and navigate, as indexing and navigation rely on the existence of transcriptions, and remain unsearchable (and potentially unusable) for both community members and linguists. In our work, we leverage the power of modern self-supervised speech-processing tools (wav2vec, Baevski et al. 2020) and the existence of archival material. We pre-trained selfsupervised models of speech processing on digitalised fieldwork recordings (350h) in Haitian Creole, collected 40 years ago in Haiti and digitalised by the French National Library. We further train the models on a speech recognition task, and obtain competitive results on fieldwork material (24.1% character error rate, CER) and read speech (15.2% CER), with models requiring only 40 minutes of transcribed speech to be trained. To the best of our knowledge, our work is the first that only uses fieldwork recordings to train state- of-the-art speech processing models at every step of the training process. We show that old fieldwork recordings, that were not collected for computational applications, can be repurposed and used to train speech recognition models. We conclude that the ‘mobilising the archive’-approach advocated by (Bird, 2020) is a promising way forward to design speech technologies for new languages, and make archival material accessible both for community members and linguists. In future works, we would like to explore query-byexample approaches that would leverage the need for transcriptions altogether and allow users to query and navigate the archive by simply pronouncing a key word. References A. Baevski, H. Zhou, A. Mohamed, and M. Auli. Wav2vec 2.0: A framework for selfsupervised learning of speech representations. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20, Red Hook, NY, USA, 2020. Curran Associates Inc. ISBN 9781713829546. S. Bird. Decolonising speech and language technology. In D. Scott, N. Bel, and C. Zong, editors, Proceedings of the 28th International Conference on Computational Linguistics, pages 3504–3519, Barcelona, Spain (Online), Dec. 2020. International Committee on Computational Linguistics. doi: 10.18653/v1/2020.coling-main.313. URL https://aclanthology.org/2020.coling-....