Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Structure-preserving attention mechanism in sequence-to-sequence neural models

Structure-preserving attention mechanism in sequence-to-sequence neural models

US Patent 11556782 · Granted Jan 17, 2023

Estimated economic value: $4,393,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Training neural networks to predict acoustic sequences using observed prosody in2023
Robust checkpoint selection for monotonic autoregressive seq2seq neural generati2023
Generating acoustic sequences via neural networks using combined prosody info2022
Voice transformation allowance determination and representation2021
Voice transformation allowance determination and representation2021
Voice-transformation based data augmentation for prosodic classification2020
Methods and systems of providing supplemental informaton2018
Coherent pitch and intensity modification of speech signals2018
Coherently-modified speech signal generation by time-dependent scaling of intens2018
Coherent pitch and intensity modification of speech signals2017
Systems and methods for encoding audio signals2017
System and method for automatic prediction of speech suitability for statistical2016