Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Methods and systems for implementing on-device non-semantic representation fine-tuning for speech classification

Methods and systems for implementing on-device non-semantic representation fine-tuning for speech classification

US Patent 11996116 · Granted May 28, 2024

Estimated economic value: $129,455,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Learned audio frontend machine learning model for audio understanding2025
Learned audio frontend machine learning model for audio understanding2025
Machine learning for microphone style transfer2025
Conditioned separation of arbitrary sounds based on machine learning models2025
Conditioned separation of arbitrary sounds based on machine learning models2025
Generating audio using auto-regressive generative neural networks2025
Systems and methods for upmixing audiovisual data2025
Method for detecting and classifying coughs or other non-semantic sounds using a2025
Audio-visual separation of on-screen sounds based on machine learning models2025
Generating coded data representations using neural networks and vector quantizer2025
Self-supervised speech representations for fake audio detection2025
Spatial audio recording from home assistant devices2025