Inventor
Alejandro Acero
Inventor
Bellevue, WA, US
Overview
Patents· 156 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G10Lprimary
G10LSpeech analysis techniques or speech synthesis60%
G06FElectric digital data processing16%
H04RLoudspeakers, microphones, gramophone pick-ups or like acoustic electromechanical transducers5%
H04MTelephonic communication3%
G06NComputing arrangements based on specific computational models3%
G06VImage or video recognition or understanding2%
H04BTransmission2%
Y10STechnical subjects covered by former uspc cross-reference art collections [xracs] and digests1%
B01DSeparation1%
B29CShaping or joining of plastics1%
PatentTitleYear
10,789,945Low-latency intelligent automated assistant202010,055,686Dimensionally reduction of linguistics information20189,984,678Factored transforms for separable adaptation of acoustic models20189,928,296'Search lexicon expansion'20189,786,284'Dual-band speech encoding and estimating a narrowband speech feature from a wideband speech feature'20179,684,741'Presenting search results according to query domains'20179,519,859'Deep structured semantic model produced using click-through data'20169,390,371'Deep convex network with joint use of nonlinear random projection, restricted boltzmann machine and batch-based parallelizable optimization'20169,264,807'Multichannel acoustic echo reduction'20169,218,412'Searching a database of listings'20159,054,764'Sensor array beamformer post-processor'20159,009,039'Noise adaptive training for speech recognition'20158,965,765'Structured models of repetition for speech recognition'20158,942,978'Parameter learning in a hidden trajectory model'20158,818,002'Robust adaptive beamforming with enhanced noise suppression'20148,818,797'Dual-band speech encoding'20148,719,019'Speaker identification'20148,700,394'Acoustic model adaptation using splines'20148,615,393'Noise suppressor for speech recognition'20138,583,428'Sound source separation using spatial filtering and regularization phases'20138,532,985'Warped spectral and fine estimate audio encoding'20138,515,096'Incorporating prior knowledge into independent component analysis'20138,489,529'Deep convex network with joint use of nonlinear random projection, Restricted Boltzmann Machine and batch-based parallelizable optimization'20138,442,828'Conditional model for natural language understanding'20138,433,576'Automatic reading tutoring with parallel polarized language modeling'20138,423,364'Generic framework for large-margin MCE training in speech recognition'20138,407,041'Integrative and discriminative technique for spoken utterance translation'20138,405,706'Visual feedback for natural head positioning'20138,401,852'Utilizing features generated from phonic units in speech recognition'20138,385,557'Multichannel acoustic echo reduction'20138,379,891'Loudspeaker array design'20138,351,589'Spatial audio for audio conferencing'20138,340,267'Audio transforms in connection with multiparty communication'20128,335,683'System for using statistical classifiers for spoken language understanding'20128,325,909'Acoustic echo suppression'20128,306,818'Discriminative training of language models for text and speech classification'20128,306,817'Speech recognition with non-linear noise reduction on Mel-frequency cepstra'20128,285,542'Adapting a language model to accommodate inputs not found in a directory assistance listing'20128,280,733'Automatic speech recognition learning using categorization and selective incorporation of user-initiated corrections'20128,239,195'Adapting a compressed model for use in speech recognition'20128,214,215'Phase sensitive model adaptation for noisy speech recognition'20128,185,389'Noise suppressor for robust speech recognition'20128,180,637'High performance HMM adaptation with joint compensation of additive and convolutive distortions'20128,180,640'Grapheme-to-phoneme conversion using acoustic data'20128,180,636'Pitch model for noise estimation'20128,165,870'Classification filter for processing data for creating a language model'20128,160,878'Piecewise-based variable-parameter Hidden Markov Models and the training thereof'20128,145,488'Parameter clustering and sharing for variable-parameter hidden markov models'20128,107,642'Spatial noise suppression for a microphone array'20128,099,279'Interactive clustering method for identifying problems in speech applications'20128,065,146'Detecting an answering machine using speech recognition'20118,019,602'Automatic speech recognition learning using user corrections'20118,019,089'Removal of noise, corresponding to user input devices from an audio signal'20118,010,356'Parameter learning in a hidden trajectory model'20118,005,237'Sensor array beamformer post-processor'20118,005,238'Robust adaptive beamforming with enhanced noise suppression'20117,991,615'Grapheme-to-phoneme conversion using acoustic data'20117,983,901'Computer-aided natural language annotation'20117,949,526'Voice aware demographic personalization'20117,941,316'Combined speech and alternate input modality to a mobile device'20117,930,178'Speech modeling and enhancement based on magnitude-normalized spectra'20117,925,502'Pitch model for noise estimation'20117,925,602'Maximum entropy model classfier that uses gaussian mean values'20117,912,707'Adapting a language model to accommodate inputs not found in a directory assistance listing'20117,885,812'Joint training of feature extraction and acoustic model parameters for speech recognition'20117,877,256'Time synchronous decoding for long-span hidden trajectory model'20117,865,357'Shareable filler model for grammar authoring'20117,860,314'Adaptation of exponential models'20107,860,707'Compound word splitting for directory assistance services'20107,856,351'Integrated speech recognition and semantic classification'20107,831,428'Speech index pruning'20107,831,425'Time-anchored posterior indexing of speech'20107,813,923'Calibration based beamforming, non-linear adaptive filtering, and multi-sensor headset'20107,809,568'Indexing and searching speech with text meta-data'20107,769,582'Method of pattern recognition using noise reduction uncertainty'20107,734,460'Time asynchronous decoding for long-span trajectory model'20107,725,314'Method and apparatus for constructing a speech filter using estimates of clean speech and noise'20107,707,029'Training wideband acoustic models in the cepstral domain using mixed-bandwidth training data for speech recognition'20107,689,419'Updating hidden conditional random field model parameters after processing individual training samples'20107,680,656'Multi-sensory speech enhancement using a speech-state model'20107,653,535'Learning statistically characterized resonance targets in a hidden trajectory model'20107,643,989'Method and apparatus for vocal tract resonance tracking using nonlinear predictor and target-guided temporal restraint'20107,643,995'Method of automatically ranking speech dialog states and transitions to aid in performance analysis in speech applications'20107,640,272'Using automated content analysis for audio/video content consumption'20097,634,406'System and method for identifying semantic intent from acoustic information'20097,634,407'Method and apparatus for indexing speech'20097,627,473'Hidden conditional random field models for phonetic classification and speech recognition'20097,624,006'Conditional maximum likelihood estimation of naïve bayes probability models'20097,620,552'Annotating programs for automatic summary generation'20097,617,098'Method of noise reduction based on dynamic aspects of speech'20097,603,267'Rules-based grammar for slots and statistical model for preterminals in natural language understanding system'20097,599,837'Creating a speech recognition grammar for alphanumeric concepts'20097,580,942'Indexing and ranking processes for directory assistance services'20097,574,008'Method and apparatus for multi-sensory speech enhancement'20097,571,097'Method for training of subspace coded gaussian models'20097,565,288'Spatial noise suppression for a microphone array'20097,565,284'Acoustic models with structured hidden dynamics with integration over many possible hidden trajectories'20097,565,292'Quantitative model for formant dynamics and contextually assimilated reduction in fluent speech'20097,548,847'System for automatically annotating training data for a natural language understanding system'20097,542,900'Noise reduction using correction vectors based on dynamic aspects of speech and noise normalization'20097,529,657'Configurable parameters for grammar authoring for speech recognition and natural language understanding'20097,519,531'Speaker adaptive learning of resonance targets in a hidden trajectory model of speech coarticulation'20097,516,067'Method and apparatus using harmonic-model-based front end for robust speech recognition'20097,478,038'Language model adaptation using semantic supervision'20097,475,011'Greedy algorithm for identifying values for vocal tract resonance vectors'20097,460,992'Method of pattern recognition using noise reduction uncertainty'20087,454,338'Training wideband acoustic models in the cepstral domain using mixed-bandwidth training data and extended vectors for speech recognition'20087,451,083'Removing noise from feature vectors'20087,447,630'Method and apparatus for multi-sensory speech enhancement'20087,424,423'Method and apparatus for formant tracking using a residual model'20087,418,383'Noise robust speech recognition with a switching linear dynamic model'20087,409,346'Two-stage implementation for phonetic recognition using a bi-directional target-filtering model of speech coarticulation and reduction'20087,406,416'Representation of a deleted interpolation N-gram language model in ARPA standard format'20087,403,894'Annotating programs for automatic summary generations'20087,383,181'Multi-sensory speech detection system'20087,379,867'Discriminative training of language models for text and speech classification'20087,363,224'Method for entering text'20087,363,221'Method of noise reduction using instantaneous signal-to-noise ratio as the principal quantity for optimal estimation'20087,346,504'Multi-sensory speech enhancement using a clean speech prior'20087,328,147'Automatic resolution of segmentation ambiguities in grammar authoring'20087,310,599'Removing noise from feature vectors'20077,289,956'System and method for user modeling to enhance named entity recognition'20077,289,955'Method of determining uncertainty associated with acoustic distortion-based noise reduction'20077,266,494'Method and apparatus for identifying noise environments from noisy signals'20077,254,536'Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech'20077,206,741'Method of speech recognition using time-dependent interpolation and hidden dynamic value classes'20077,200,557'Method of reducing index sizes used to represent spectral content vectors'20077,181,390'Noise reduction using correction vectors based on dynamic aspects of speech and noise normalization'20077,174,292'Method of determining uncertainty associated with acoustic distortion-based noise reduction'20077,165,026'Method of noise estimation using incremental bayes learning'20077,139,703'Method of iterative noise estimation in a recursive framework'20067,117,153'Method and apparatus for predicting word error rates from text'20067,117,148'Method of noise reduction using correction vectors based on dynamic aspects of speech and noise normalization'20067,107,210'Method of noise reduction based on dynamic aspects of speech'20067,103,544'Method and apparatus for predicting word error rates from text'20067,103,540'Method of pattern recognition using noise reduction uncertainty'20067,080,004'Grammar authoring system'20067,050,975'Method of speech recognition using time-dependent interpolation and hidden dynamic value classes'20067,047,189'Sound source separation using convolutional mixing and a priori sound source knowledge'20067,047,047'Non-linear observation model for removing noise from corrupted signals'20067,028,325'Annotating programs for automatic summary generation'20067,003,455'Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech'20066,990,447'Method and apparatus for denoising and deverberation using variational inference and strong speech models'20066,985,858'Method and apparatus for removing noise from feature vectors'20066,959,276'Including the category of environmental noise when processing speech signals'20056,944,590'Method of iterative noise estimation in a recursive framework'20056,879,952'Sound source separation using convolutional mixing and a priori sound source knowledge'20056,708,154'Method and apparatus for using formant models in resonance control for speech systems'20046,505,152'Method and apparatus for using formant models in speech systems'20036,253,182'Method and apparatus for speech synthesis with efficient spectral smoothing'20016,226,606'Method and apparatus for pitch tracking'20016,163,769'Text-to-speech using clustered context-dependent phoneme-based units'20005,913,193'Method and system of runtime acoustic unit selection for speech synthesis'19995,734,791'Rapid tree-based method for vector quantization'19985,604,839'Method and system for improving speech recognition through front-end normalization of feature vectors'19975,535,305'Sub-partitioned vector quantization of probability density functions'1996Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
1996–1998Based in Madrid, ES· patent location history
1997–2016Patents assigned to MICROSOFT CORP (143)· patent assignee history
1997–2009Based in Redmond, WA, US· patent location history
2005–2018Based in Bellevue, WA, US· patent location history
2011–2018Patents assigned to ACERO ALEJANDRO (44)· patent assignee history
2011–2015Patents assigned to YU DONG (16)· patent assignee history
2012–2015Patents assigned to DENG LI (12)· patent assignee history
2015–2018Patents assigned to MICROSOFT TECHNOLOGY LICENSING LLC (11)· patent assignee history
2020Based in Monte Sereno, CA, US· patent location history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| MICROSOFT CORP | 143 | 1997–2016 |
| ACERO ALEJANDROself | 44 | 2011–2018 |
| YU DONG | 16 | 2011–2015 |
| DENG LI | 12 | 2012–2015 |
| MICROSOFT TECHNOLOGY LICENSING LLC | 11 | 2015–2018 |
Locations
| Location | Patents | Span |
|---|---|---|
| Bellevue, Washington, US | 145 | 2005–2018 |
| Redmond, Washington, US | 8 | 1997–2009 |
| Madrid, ES | 2 | 1996–1998 |
| Monte Sereno, California, US | 1 | 2020 |