Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Generating representations of acoustic sequences

Generating representations of acoustic sequences

US Patent 10535338 · Granted Jan 14, 2020

Estimated economic value: $42,883,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Speaker-turn-based online speaker diarization with constrained spectral clusteri2025
Predicting protein structures using geometry neural networks that estimate simil2025
Determining protein distance maps by combining distance maps crops2025
Protein structure prediction using geometric attention neural networks2025
Contrastive Siamese network for semi-supervised speech recognition2025
Semi-supervised training scheme for speech recognition2025
End-to-end multi-talker overlapping speech recognition2025
One model unifying streaming and non-streaming speech recognition2025
Speech recognition using neural networks2025
Protein structure prediction from amino acid sequences using self-attention neur2024
Asynchronous optimization for sequence training of neural networks2024
Reducing streaming ASR model delay with self alignment2024