G10L 25/03
Speech or voice analysis techniques not restricted to a single one of
Official title: characterised by the type of extracted parameters
G10L25/03 (Speech or voice analysis techniques not restricted to a single one of) appears on 3,561 US grants and 3,844 published applications in this corpus.
Search patents in G10L- Granted patents
- 3,561
- Published applications
- 3,844
- Assignees
- 1,223
- Inventors
- 6,842
- Latest grant
- 6 Oct 2026
Filings by year
| Year | Granted patents | Published applications |
|---|---|---|
| 1977 | 1 | 0 |
| 1978 | 0 | 0 |
| 1979 | 0 | 0 |
| 1980 | 0 | 0 |
| 1981 | 0 | 0 |
| 1982 | 0 | 0 |
| 1983 | 1 | 0 |
| 1984 | 1 | 0 |
| 1985 | 1 | 0 |
| 1986 | 3 | 0 |
| 1987 | 3 | 0 |
| 1988 | 2 | 0 |
| 1989 | 4 | 0 |
| 1990 | 14 | 0 |
| 1991 | 6 | 0 |
| 1992 | 7 | 0 |
| 1993 | 13 | 0 |
| 1994 | 13 | 0 |
| 1995 | 17 | 0 |
| 1996 | 14 | 0 |
| 1997 | 49 | 0 |
| 1998 | 74 | 0 |
| 1999 | 37 | 0 |
| 2000 | 27 | 0 |
| 2001 | 16 | 6 |
| 2002 | 14 | 21 |
| 2003 | 15 | 12 |
| 2004 | 17 | 21 |
| 2005 | 8 | 30 |
| 2006 | 15 | 34 |
| 2007 | 13 | 33 |
| 2008 | 21 | 32 |
| 2009 | 19 | 35 |
| 2010 | 27 | 31 |
| 2011 | 28 | 44 |
| 2012 | 40 | 78 |
| 2013 | 55 | 102 |
| 2014 | 63 | 93 |
| 2015 | 96 | 125 |
| 2016 | 136 | 198 |
| 2017 | 213 | 249 |
| 2018 | 217 | 278 |
| 2019 | 333 | 362 |
| 2020 | 305 | 343 |
| 2021 | 265 | 348 |
| 2022 | 341 | 363 |
| 2023 | 278 | 324 |
| 2024 | 307 | 305 |
| 2025 | 259 | 216 |
| 2026 | 173 | 161 |
By publication year. Applications have been published since 2001. 2026 runs to 8 Oct.
Subgroups
Granted patents
- G10L 25/18The extracted parameters being spectral information of each sub-band1,549
- G10L 25/21The extracted parameters being power information1,023
- G10L 25/06The extracted parameters being correlation coefficients486
- G10L 25/24The extracted parameters being the cepstrum433
- G10L 25/12The extracted parameters being prediction coefficients255
- G10L 25/15The extracted parameters being formant information222
- G10L 25/09The extracted parameters being zero crossing rates94
Recent patents
- Method for evaluating possibility of dysphagia by analyzing acoustic signals, and server and non-transitory computer-readable recording medium performing same6 Oct 2026US 12,751,662 B2Dain Technology, Inc.
- Method of contextual speech decoding from the brain6 Oct 2026US 12,755,738 B2The Regents of the University of California
- Audio content recognition method and system6 Oct 2026US 12,755,751 B2Gracenote, Inc.
- Oral function evaluation device, oral function evaluation system, and oral function evaluation method6 Oct 2026US 12,755,752 B2Panasonic Intellectual Property Management Co., Ltd.
- Wearable device with blocked sensor detection6 Oct 2026US 12,756,983 B2Bose Corporation
- Minimizing gunshot detection false positives8 Oct 2026US 2026/0311718 A1Utility Associates, Inc.
- Multi-modal controllable video-to-audio generation8 Oct 2026US 2026/0311719 A1
- Systems and methods for generating context-oriented summary of audio conversations in real time1 Oct 2026US 2026/0301733 A1Genesys Cloud Services, Inc.
- Systems and Methods for Personalized Sound Localization in a Conversation1 Oct 2026US 2026/0301745 A1Google Inc.
- Method and system for classifying an acoustic environment1 Oct 2026US 2026/0301759 A1Dolby Laboratories Licensing Corporation
Most cited
By later US patents
- Patient monitor alarm speaker analyzer468US 10,779,098 B2Masimo Corporation · 2020
- Mode-specific method and apparatus for encoding signals containing speech339US 5,596,676 AHughes Electronics Corporation · 1997
- Apparatus and method for encoding a multi-channel audio signal314US 8,577,045 B2Motorola Mobility LLC · 2013
- Concatenation of speech segments by use of a speech synthesizer308US 6,366,883 B1ATR Interpreting Telecommunications · 2002
- Methods and devices for ignoring similar audio being received by a system279US 9,728,188 B1Amazon Technologies, Inc. · 2017