Inventor
Masafumi Nishimura
Inventor
Yokohama, JP
Overview
Patents· 62 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G10Lprimary
G10LSpeech analysis techniques or speech synthesis83%
G06FElectric digital data processing9%
G01SRadio direction-finding1%
G06NComputing arrangements based on specific computational models1%
G09BEducational or demonstration appliances1%
H04MTelephonic communication1%
H04RLoudspeakers, microphones, gramophone pick-ups or like acoustic electromechanical transducers1%
Y10STechnical subjects covered by former uspc cross-reference art collections [xracs] and digests1%
PatentTitleYear
10,418,029Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods20199,978,364Pronunciation accuracy in speech recognition20189,934,776Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods20189,892,727'Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods'20189,747,893'Unsupervised training method, training apparatus, and training program for an N-gram language model based upon recognition reliability'20179,626,957'Speech retrieval method, speech retrieval apparatus, and program for speech retrieval apparatus'20179,626,958'Speech retrieval method, speech retrieval apparatus, and program for speech retrieval apparatus'20179,601,110'Unsupervised training method for an N-gram language model based upon recognition reliability'20179,536,518'Unsupervised training method, training apparatus, and training program for an N-gram language model based upon recognition reliability'20179,384,730'Pronunciation accuracy in speech recognition'20169,378,736'Speech retrieval method, speech retrieval apparatus, and program for speech retrieval apparatus'20169,373,328'Speech retrieval method, speech retrieval apparatus, and program for speech retrieval apparatus'20169,311,291'Correcting N-gram probabilities by page view information'20169,275,631'Speech synthesis system, speech synthesis program product, and speech synthesis method'20169,269,357'System and method for extracting a specific situation from a conversation'20169,251,135'Correcting N-gram probabilities by page view information'20169,165,553'Information processing device, large vocabulary continuous speech recognition method and program including hypothesis ranking'20159,070,375'Voice activity detection system, method, and program product'20159,002,843'System and method for extraction of off-topic part from conversation'20158,972,407'Information processing method for determining weight of each feature in subjective hierarchical clustering'20158,930,185'Speech feature extraction apparatus, speech feature extraction method, and speech feature extraction program'20158,918,396'Information processing apparatus, method and program for determining weight of each feature in subjective hierarchical clustering'20148,812,312'System, method and program for speech processing'20148,762,137'Target voice extraction method, apparatus and program product'20148,751,235'Annotating phonemes and accents for text-to-speech system'20148,744,853'Speaker-adaptive synthesized voice'20148,712,770'Method, preprocessor, speech recognition system, and program product for extracting target speech by removing noise'20148,566,084'Speech processing based on time series of maximum values of cross-power spectrum phase between two consecutive speech frames'20138,468,016'Speech feature extraction apparatus, speech feature extraction method, and speech feature extraction program'20138,370,149'Speech synthesis system, speech synthesis program product, and speech synthesis method'20138,165,874'System, method, and program product for processing speech ratio difference data variations in a conversation between two persons'20128,165,317'Method and system for position detection of a sound source'20128,150,693'Methods and apparatus for natural spoken language speech recognition'20128,150,687'Recognizing speech, and processing data'20128,065,149'Unsupervised lexicon acquisition from speech and text'20118,024,184'Speech recognition device, speech recognition method, computer-executable program for causing computer to execute recognition method, and storage medium'20118,015,011'Generating objectively evaluated sufficiently natural synthetic speech from text by using selective paraphrases'20118,000,966'Methods and apparatus for natural spoken language speech recognition with word prediction'20117,921,014'System and method for supporting text-to-speech'20117,895,038'Signal enhancement via noise reduction for speech recognition'20117,856,353'Method for processing speech signal data with reverberation filtering'20107,747,443'Apparatus, method, and program for supporting speech interface design'20107,729,921'Apparatus, method, and program for supporting speech interface design'20107,720,679'Speech recognition apparatus, speech recognition apparatus and program thereof'20107,660,717'Speech recognition system and program thereof'20107,599,836'Voice recording system, recording device, voice analysis device, voice recording method and program'20097,590,526'Method for processing speech signal data and finding a filter coefficient'20097,533,015'Signal enhancement via noise reduction for speech recognition'20097,480,612'Word predicting method, voice recognition method, and voice recognition apparatus and program using the same methods'20097,478,041'Speech recognition apparatus, speech recognition apparatus and program thereof'20097,403,896'Speech recognition system and program thereof'20087,359,852'Systems and methods for natural spoken language word prediction and speech recognition'20086,985,863'Speech recognition apparatus and method utilizing a language model prepared for expressions unique to spontaneous speech'20066,917,910'Method, apparatus, computer system and storage medium for speech recognition'20056,778,958'Symbol insertion apparatus and method'20045,671,330'Speech synthesis using glottal closure instants determined from adaptively-thresholded wavelet transforms'19975,502,791'Speech recognition by concatenating fenonic allophone hidden Markov models in parallel among subwords'19965,353,377'Speech recognition system having an interface to a host computer bus for direct access to the host memory'19945,050,215'Speech recognition method'19915,046,099'Adaptation of acoustic prototype vectors in a speech recognition system'19915,031,217'Speech recognition system using Markov models having independent label output sets'19914,829,577'Speech recognition method'1989Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
1989–2019Patents assigned to IBM (40)· patent assignee history
1989–2018Based in Yokohama, JP· patent location history
1991–2019Based in Kanagawa, JP· patent location history
2009–2016Patents assigned to NUANCE COMMUNICATIONS INC (20)· patent assignee history
2011–2016Patents assigned to NISHIMURA MASAFUMI (18)· patent assignee history
2012–2015Patents assigned to ICHIKAWA OSAMU (8)· patent assignee history
2013–2015Patents assigned to FUKUDA TAKASHI (6)· patent assignee history
2015Based in Tokyo, JP· patent location history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| IBM | 40 | 1989–2019 |
| NUANCE COMMUNICATIONS INC | 20 | 2009–2016 |
| NISHIMURA MASAFUMIself | 18 | 2011–2016 |
| ICHIKAWA OSAMU | 8 | 2012–2015 |
| FUKUDA TAKASHI | 6 | 2013–2015 |
Locations
| Location | Patents | Span |
|---|---|---|
| Yokohama, JP | 35 | 1989–2018 |
| Kanagawa, JP | 26 | 1991–2019 |
| Tokyo, JP | 1 | 2015 |