Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Very deep convolutional neural networks for end-to-end speech recognition

Very deep convolutional neural networks for end-to-end speech recognition

US Patent 11080599 · Granted Aug 3, 2021

Estimated economic value: $104,518,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Generating images using sequences of generative neural networks2025
Anti-tumor compound and preparation method and use thereof2025
End-to-end speech waveform generation through data density gradient estimation2025
End-to-end speech waveform generation through data density gradient estimation2025
Using aligned text and speech representations to train automatic speech recognit2025
Image-to-image mapping by iterative de-noising2025
Convolution-augmented transformer models2025
Two-level speech prosody transfer2025
Generating structured text content using speech recognition models2025
Generating videos using sequences of generative neural networks2025
Advancing the use of text and speech in ASR pretraining with consistency and con2025
Two-level text-to-speech systems using synthetic training data2025