biostudies-literatureLaptev AITMO University3063https://www.ebi.ac.uk/biostudies/studies/S-EPMC8124527biostudies-literatureUnknown21(9)With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR systems as they can be made resource-efficient while maintaining a higher quality compared to hybrid systems. However, building end-to-end models requires a significant amount of speech data. Personalization, which is mainly handling out-of-vocabulary (OOV) words, is another challenging task associated with speech assistants. In this work, we consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate, embodied in Babel Turkish and Babel Georgian tasks. We propose a method of dynamic acoustic unit augmentation baSensors (Basel, Switzerland)Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition.PMC8124527620173Mitrofanov AMedennikov IMatveev YLaptev AAndrusenko APodluzhny IfalseDynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition.With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR systems as they can be made resource-efficient while maintaining a higher quality compared to hybrid systems. However, building end-to-end models requires a significant amount of speech data. Personalization, which is mainly handling out-of-vocabulary (OOV) words, is another challenging task associated with speech assistants. In this work, we consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate, embodied in Babel Turkish and Babel Georgian tasks. We propose a method of dynamic acoustic unit augmentation ba2021-01-01T00:00:00Z2021 Apr2025-04-04T11:58:17.869Z2022-02-10T10:46:18.508ZS-EPMC81245273392479810.3390/s21093063