Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Speaker diarization using speaker embedding(s) and trained generative model

Speaker diarization using speaker embedding(s) and trained generative model

US Patent 10978059 · Granted Apr 13, 2021

Estimated economic value: $106,151,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Speaker-turn-based online speaker diarization with constrained spectral clusteri2025
Targeted voice separation by speaker conditioned on spectrogram masking2025
Speaker awareness using speaker dependent speech model(s)2025
Methods and apparatus for bypassing holds2025
Targeted voice separation by speaker for speech recognition2025
Automatically determining language for speech recognition of spoken utterance re2025
Speech recognition using neural networks2025
Speech synthesis utilizing audio waveform difference signal(s)2025
Identification and utilization of misrecognitions in automatic speech recognitio2024
Text independent speaker recognition2024
Mixing heterogeneous loss types to improve accuracy of keyword spotting2024
Automatically determining language for speech recognition of spoken utterance re2024