Patents
US 9520124 B2: Discriminative training of document transcription system
- Granted
- 2016-12-13
- Filed
- 2015-11-16 application 14942349
- Type
- Utility · 8 claims
- Elsewhere
- Google Patents ↗ · USPTO patent document ↗ · USPTO Patent Center record ↗
Abstract
A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.
Source: PVGPATDIS, file of 2026-04-10 (ipg161213.xml).
Assignees
| Assignee | Type | Place | Also on furp.org | Source |
|---|---|---|---|---|
| MMODAL IP LLC 47 patents | US company or organization | Franklin, TN | PVGPATDIS, file of 2026-04-10 |
Inventors
| Inventor | Place | Patents | Person page | Source |
|---|---|---|---|---|
| Lambert Mathias | Seattle, WA | 23 | PVGPATDIS, file of 2026-04-10 | |
| Girija Yegnanarayanan | Raleigh, NC | 22 | PVGPATDIS, file of 2026-04-10 | |
| Juergen Fritsch | Pittsburgh, PA | 27 | PVGPATDIS, file of 2026-04-10 |
CPC categories
| Subclass | Category | First group | Source |
|---|---|---|---|
| G10L | Speech analysis techniques or speech synthesis; speech recognition; speech or voice processing techniques; speech or audio coding or decoding | G10L15/063 | PVGPATDIS, file of 2026-04-10 |
| G06F | Electric digital data processing | G06F40/211 | PVGPATDIS, file of 2026-04-10 |
| G16H | Healthcare informatics, i.e. information and communication technology [ict] specially adapted for the handling or processing of medical or healthcare data | G16H15/00 | PVGPATDIS, file of 2026-04-10 |
Cooperative Patent Classification, as currently assigned (one row per subclass).
Assignments and security interests
| Recorded | What | From | To | Reel/frame | Source |
|---|---|---|---|---|---|
| 2024-02-01 | Assignment Assignment of assignor's interest | 3M INNOVATIVE PROPERTIES COMPANY signed 2024-02-01 | SOLVENTUM INTELLECTUAL PROPERTIES COMPANY MAPLEWOOD, MN | 66435/347 | PASDL, file of 2026-10-15 |
| 2021-10-22 | Assignment Assignment of assignor's interest | MMODAL IP LLC signed 2021-05-06 | 3M INNOVATIVE PROPERTIES COMPANY SAINT PAUL, MN | 57883/129 | PASDL, file of 2026-10-15 |
| 2017-04-14 | Name change Change of address | MMODAL IP LLC signed 2014-08-05 | MMODAL IP LLC FRANKLIN, TN | 42271/858 | PASDL, file of 2026-10-15 |
| 2016-05-16 | Assignment Assignment of assignor's interest | MATHIAS, LAMBERT signed 2013-06-20 YEGNANARAYANAN, GIRIJA signed 2013-06-20 FRITSCH, JUERGEN signed 2013-06-20 | MMODAL IP LLC FRANKLIN, TN | 38607/177 | PASDL, file of 2026-10-15 |
Documents recorded with the USPTO Assignment Recordation Branch that list this patent. A security interest is a lender’s claim on the patent as collateral; a release ends it.
USPTO bulk data: PatentsView granted patents, disambiguated (PVGPATDIS) for patents, assignees, inventors, places and CPC categories; the USPTO Patent Assignment Dataset (ECORSEXC) for assignments and security interests. Patents filed in the last 20 years. No claims or full text. Links to other records are by name (and state): EXACT means the identical full name and state; FUZZY means a looser name match, with the confidence shown.