Today, speech technology is only available for a small fraction of the thousands of languages spoken around the world because traditional systems need to be trained on large amounts of annotated speech audio with transcriptions. Obtaining that kind of data for every human language and dialect is almost impossible.
Wav2vec works around this limitation by requiring little to no transcribed data. The model uses self-supervision to push the boundaries by learning from unlabeled training data. This enables speech recognition systems for many more languages and dialects, such as Kyrgyz and Swahili, which don’t have a lot of transcribed speech audio. Self-supervision is the key to leveraging unannotated data and building better systems.
A. Razavi, S. Matwin, D. Inkpen, и A. Kouznetsov. ICDMW '09: Proceedings of the 2009 IEEE International Conference on Data Mining Workshops, стр. 471--476. Washington, DC, USA, IEEE Computer Society, (2009)
M. Richardson, A. Prakash, и E. Brill. Proceedings of the 15th international conference on World Wide Web, стр. 707--715. Edinburgh, Scotland, ACM Press, (мая 2006)
S. Riedel, L. Yao, и A. McCallum. Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III, стр. 148--163. Berlin, Heidelberg, Springer-Verlag, (2010)