| Title |
Evaluation of Lithuanian speech-to-text transcribers |
| Authors |
Kasparaitis, Pijus |
| DOI |
10.15388/25-INFOR591 |
| Full Text |
|
| Is Part of |
Informatica.. Vilnius : Vilniaus universiteto leidykla. 2025, vol. 36, no. 2, p. 369-384.. ISSN 0868-4952. eISSN 1822-8844 |
| Keywords [eng] |
speech-to-text transcription ; automatic speech recognition ; word error rate ; character error rate ; Lithuanian |
| Abstract [eng] |
For more than two decades, Lithuanian speech recognition has been researched solely in Lithuania due to the need for deep knowledge of Lithuanian. AI advancements now allow high-quality speech-to-text systems to be built without native knowledge, given sufficient annotated data is available. This study evaluated as many as 18 Lithuanian speech transcribers using a small piece of recording; 7 best ones were selected and evaluated using extensive data. The top system achieved a WER of 5.1% for Lithuanian words, with three others showing 8.7–9.2%. For other word-size tokens, such as numbers, speech disfluencies, abbreviations, foreign words, a classification adapted to the Lithuanian language was proposed. Different processing strategies for tokens of these classes were examined and it was assessed which transcribers tend to follow which strategies. |
| Published |
Vilnius : Vilniaus universiteto leidykla |
| Type |
Journal article |
| Language |
English |
| Publication date |
2025 |
| CC license |
|
