Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Training and using a transcript generation model on a multi-speaker audio stream

Training and using a transcript generation model on a multi-speaker audio stream

US Patent 11984127 · Granted May 14, 2024

Estimated economic value: $541,703,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Laser device and laser projection apparatus2025
Adjustable dumbbell2025
Dumbbell2025
Lateral electro-conduction device and method for multi-wire submerged arc inner/2025
Channel information processing method and apparatus2025
Weather station2025
Method for detecting multicast service flow and related apparatus2025
Hypothesis stitcher for speech recognition of long-form audio2025
Hypothesis stitcher for speech recognition of long-form audio2025
Hypothesis stitcher for speech recognition of long-form audio2025
Hypothesis stitcher for speech recognition of long-form audio2025
Hypothesis stitcher for speech recognition of long-form audio2025