Automatic Speech Recognition of Low-Resource Languages Based on Chukchi
This work addresses the challenge of ASR for low-resource and polysynthetic languages, which is incremental as it applies an existing method to new data.
The paper tackled the problem of automatic speech recognition for the low-resource and polysynthetic Chukchi language by collecting 21:34:23 hours of audio and 112,719 sentences of text, and training an XLSR model that showed good results using CER metrics.
The following paper presents a project focused on the research and creation of a new Automatic Speech Recognition (ASR) based in the Chukchi language. There is no one complete corpus of the Chukchi language, so most of the work consisted in collecting audio and texts in the Chukchi language from open sources and processing them. We managed to collect 21:34:23 hours of audio recordings and 112,719 sentences (or 2,068,273 words) of text in the Chukchi language. The XLSR model was trained on the obtained data, which showed good results even with a small amount of data. Besides the fact that the Chukchi language is a low-resource language, it is also polysynthetic, which significantly complicates any automatic processing. Thus, the usual WER metric for evaluating ASR becomes less indicative for a polysynthetic language. However, the CER metric showed good results. The question of metrics for polysynthetic languages remains open.