CLAIJul 1, 2022

Swiss German Speech to Text system evaluation

arXiv:2207.00412v27 citationsh-index: 14
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of accurate speech-to-text conversion for Swiss German, a low-resource language, but is incremental as it compares existing methods on new data.

The researchers evaluated four commercial speech-to-text systems and their own model for Swiss German, finding that their model achieved the highest BLEU scores of 0.607 and 0.722 on two datasets, outperforming the best commercial system which scored 0.509 and 0.568.

We present an in-depth evaluation of four commercially available Speech-to-Text (STT) systems for Swiss German. The systems are anonymized and referred to as system a-d in this report. We compare the four systems to our STT model, referred to as FHNW from hereon after, and provide details on how we trained our model. To evaluate the models, we use two STT datasets from different domains. The Swiss Parliament Corpus (SPC) test set and a private dataset in the news domain with an even distribution across seven dialect regions. We provide a detailed error analysis to detect the three systems' strengths and weaknesses. This analysis is limited by the characteristics of the two test sets. Our model scored the highest bilingual evaluation understudy (BLEU) on both datasets. On the SPC test set, we obtain a BLEU score of 0.607, whereas the best commercial system reaches a BLEU score of 0.509. On our private test set, we obtain a BLEU score of 0.722 and the best commercial system a BLEU score of 0.568.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes