LexDanaLexDanabeta
Inventor

Andrej Ljolje

Inventor
Morris Plains, NJ, US

Overview

59→
Patents
2009–2020
Patent span
Physics
Primary field (CPC G)

Patents· 59 as inventor

Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.

G10Lprimary
G10LSpeech analysis techniques or speech synthesis69%
G06FElectric digital data processing15%
H04NPictorial communication, e.g. television8%
G06QInformation and communication technology [ict] specially adapted for administrative, commercial, financial, managerial or supervisory purposes5%
G11BInformation storage based on relative movement between record carrier and transducer3%
Y10STechnical subjects covered by former uspc cross-reference art collections [xracs] and digests1%
PatentTitleYear
10,699,702System and method for personalization of acoustic models for automatic speech recognition202010,504,505System and method for speech personalization by need201910,291,966Systems and methods of providing modified media content201910,199,035Multi-channel speech recognition20199,984,679System and method for optimizing speech recognition and natural language parameters with user feedback20189,934,792Automatic disclosure detection20189,880,996'System and method for increasing recognition rates of in-vocabulary words by improving pronunciation modeling'20189,837,071System and method for speech personalization by need20179,837,072System and method for personalization of acoustic models for automatic speech recognition20179,773,497'System and method for handling missing speech data'20179,653,069'System and method for personalization of acoustic models for automatic speech recognition'20179,628,741'Systems and methods of providing modified media content'20179,607,279'Automatic disclosure detection'20179,576,582'System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring'20179,484,024'System and method for handling repeat queries due to wrong ASR output by modifying an acoustic, a language and a semantic model'20169,484,019'System and method for discriminative pronunciation modeling for voice search'20169,431,005'System and method for supplemental speech recognition by identified idle resources'20169,431,011'System and method for pronunciation modeling'20169,414,010'Systems and methods of providing modified media content'20169,396,725'System and method for optimizing speech recognition and natural language parameters with user feedback'20169,336,773'System and method for standardized speech recognition infrastructure'20169,305,546'System and method for handling missing speech data'20169,305,547'System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring'20169,165,555'Low latency real-time vocal tract length normalization'20159,053,704'System and method for standardized speech recognition infrastructure'20159,037,465'Automatic disclosure detection'20159,026,442'System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring'20159,026,444'System and method for personalization of acoustic models for automatic speech recognition'20159,002,713'System and method for speech personalization by need'20158,990,085'System and method for handling repeat queries due to wrong ASR output by modifying an acoustic, a language and a semantic model'20158,909,527'Low latency real-time vocal tract length normalization'20148,892,441'System and method for increasing recognition rates of in-vocabulary words by improving pronunciation modeling'20148,862,470'System and method for pronunciation modeling'20148,812,315'System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring'20148,781,831'System and method for standardized speech recognition infrastructure'20148,756,065'Correlated call analysis for identified patterns in call transcriptions'20148,751,229'System and method for handling missing speech data'20148,738,375'System and method for optimizing speech recognition and natural language parameters with user feedback'20148,612,234'Multi-state barge-in models for spoken dialog systems'20138,600,749'System and method for training adaptation-specific acoustic models for automatic speech recognition'20138,589,163'Adapting language models with a bit mask for a subset of related words'20138,548,807'System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring'20138,532,993'Speech recognition based on pronunciation modeling'20138,532,992'System and method for standardized speech recognition infrastructure'20138,428,443'Systems and methods of providing modified media content'20138,412,527'Automatic disclosure detection'20138,374,867'System and method for standardized speech recognition infrastructure'20138,346,549'System and method for supplemental speech recognition by identified idle resources'20138,312,492'Systems and methods of providing modified media content'20128,296,141'System and method for discriminative pronunciation modeling for voice search'20128,214,213'Speech recognition based on pronunciation modeling'20128,204,359'Systems and methods of providing modified media content'20128,095,365'System and method for increasing recognition rates of in-vocabulary words by improving pronunciation modeling'20128,073,693'System and method for pronunciation modeling'20118,046,221'Multi-state barge-in models for spoken dialog systems'20118,024,191'System and method of word lattice augmentation using a pre/post vocalic consonant distinction'20118,015,008'System and method of using acoustic models for automatic speech recognition which distinguish pre- and post-vocalic consonants'20118,000,971'Discriminative training of multi-state barge-in models for speech processing'20117,567,903'Low latency real-time vocal tract length normalization'2009

Career & activity timeline

Assembled from patent assignee/location history and declaration credentials.

2009–2015Patents assigned to AT & T IP II LP (7)· patent assignee history
2009–2019Based in Morristown, NJ, US· patent location history
2011–2019Patents assigned to AT & T IP I LP (40)· patent assignee history
2011–2016Patents assigned to LJOLJE ANDREJ (25)· patent assignee history
2011–2015Patents assigned to CONKIE ALISTAIR D (9)· patent assignee history
2011–2020Based in Morris Plains, NJ, US· patent location history
2017–2020Patents assigned to NUANCE COMMUNICATIONS INC (9)· patent assignee history

Inventor activity

Assignee and location history derived from the patent record.

Assignees
AssigneePatentsSpan
AT & T IP I LP402011–2019
LJOLJE ANDREJself252011–2016
CONKIE ALISTAIR D92011–2015
NUANCE COMMUNICATIONS INC92017–2020
AT & T IP II LP72009–2015
Locations
LocationPatentsSpan
Morris Plains, New Jersey, US482011–2020
Morristown, New Jersey, US112009–2019