Inventor · Bellevue, WA, US

Takuya Yoshioka

25Patents
5h-index
35Co-inventors
65Inventor score

Filing activity: Feb 16, 2007 → Feb 13, 2024

Most-cited inventions

PatentTitleAreaCited byStatus
US10957337B2 Multi-microphone speech separation Physics 73 Active
US10743107B1 Synchronization of audio signals from distributed devices Electricity 70 Active
US10839822B2 Multi-channel speech separation Electricity 13 Active
US10812921B1 Audio stream processing for distributed device meeting Electricity 8 Active
US8467538B2 Dereverberation apparatus, dereverberation method, dereverberation program, and recording medium Physics 7 Active
US11023690B2 Customized output to optimize for user preference in a distributed system Physics 4 Active
US8848933B2 Signal enhancement device, method thereof, program, and recording medium Physics 4 Active
US11468895B2 Distributed device meeting initiation Physics 3 Active
US11264044B2 Acoustic model training method, speech recognition method, acoustic model training apparatus, speech recognition apparatus, acoustic model training program, and speech recognition program Physics 3 Active
US11138980B2 Processing overlapping speech from distributed devices Physics 3 Active
US11445295B2 Low-latency speech separation Physics 1 Active
US10643633B2 Spatial correlation matrix estimation device, spatial correlation matrix estimation method, and spatial correlation matrix estimation program Physics 1 Active
US11322148B2 Speaker attributed transcript generation Electricity 1 Active
US12394420B2 Hypothesis stitcher for speech recognition of long-form audio Physics 0 Active
US12243534B2 Speaker attributed transcript generation Electricity 0 Active
US11922963B2 Systems and methods for human listening and live captioning Physics 0 Active
US11875796B2 Audio-visual diarization to identify meeting attendees Physics 0 Active
US8494845B2 Signal distortion elimination apparatus, method, program, and recording medium having the program recorded thereon Physics 0 Active
US11984127B2 Training and using a transcript generation model on a multi-speaker audio stream Physics 0 Active
US9754608B2 Noise estimation apparatus, noise estimation method, noise estimation program, and recording medium Physics 0 Active
US11935542B2 Hypothesis stitcher for speech recognition of long-form audio Physics 0 Active
US12230259B2 Array geometry agnostic multi-channel personalized speech enhancement Physics 0 Active
US12051422B2 Processing overlapping speech from distributed devices Physics 0 Active
US11574639B2 Hypothesis stitcher for speech recognition of long-form audio Physics 0 Active
US10856076B2 Low-latency speech separation Physics 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.