Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings

Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings

US Patent 11568858 · Granted Jan 31, 2023

Estimated economic value: $7,725,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Length perturbation techniques for improving generalization of deep neural netwo2025
Textual knowledge transfer for improved speech recognition and understanding2025
Textual knowledge transfer for improved speech recognition and understanding2025
Multi-speaker data augmentation for improved end-to-end automatic speech recogni2025
Multi-speaker data augmentation for improved end-to-end automatic speech recogni2025
Reducing exposure bias in machine learning training of sequence-to-sequence tran2024
Training of model for processing sequence data2024
Integrating dialog history into end-to-end spoken language understanding systems2024
Integrating dialog history into end-to-end spoken language understanding systems2024
Mixture model attention for flexible streaming and non-streaming automatic speec2024
End-to-end integration of dialog history for spoken language understanding2024
End-to-end integration of dialog history for spoken language understanding2024