new TOP 200 Companies filing patents this week

new Companies with the Most Patent Filings

Yifan Gong patents

Recent patents with Yifan Gong listed as an inventor - additional entries may be under other spellings.

Yifan Gong - Related organizations: Microsoft Technology Licensing, Llc patents, Microsoft Corporation patents

Automatic speech recognition confidence classifier

03/16/17 - 20170076725 - The described technology provides normalization of speech recognition confidence classifier (CC) scores that maintains the accuracy of acceptance metrics. A speech recognition CC scores quantitatively represents the correctness of decoded utterances in a defined range (e.g., [0,1]). An operating threshold is associated with a confidence classifier, such that utterance recognitions
Inventors: Kshitiz Kumar, Yifan Gong, Chaojun Liu

Deep neural support vector machines

10/20/16 - 20160307565 - Aspects of the technology described herein relate to a new type of deep neural network (DNN). The new DNN is described herein as a deep neural support vector machine (DNSVM). Traditional DNNs use the multinomial logistic regression (softmax activation) at the top layer and underlying layers for training. The new
Inventors: Chaojun Liu, Kaisheng Yao, Yifan Gong, Shixiong Zhang

Small-footprint deep neural network

10/20/16 - 20160307095 - Conversion of a large-footprint DNN to a small-print DNN is performed using a variety of techniques, including split-vector quantization. The small-foot print DNN may be distributed to a variety of devices, including mobile devices. Further, the small-footprint DNN may aid a digital assistant on a device in interpreting speech input.
Inventors: Jinyu Li, Yifan Gong, Yongqiang Wang

Speech recognition error diagnosis

09/01/16 - 20160253989 - Techniques and technologies for diagnosing speech recognition errors are described. In an example implementation, a system for diagnosing speech recognition errors may include an error detection module configured to determine that a speech recognition result is least partially erroneous, and a recognition error diagnostics module. The recognition error diagnostics module
Inventors: Shiun-zu Kuo, Thomas Reutter, Yifan Gong, Mark T. Hanson, Ye Tian, Shuangyu Chang, Jon Hamaker, Qi Miao, Yuancheng Tu

Learning student dnn via output distribution

03/17/16 - 20160078339 - Systems and methods are provided for generating a DNN classifier by “learning” a “student” DNN model from a larger more accurate “teacher” DNN model. The student DNN may be trained from un-labeled training data because its supervised signal is obtained by passing the un-labeled training data through the teacher DNN.
Inventors: Jinyu Li, Rui Zhao, Jui-ting Huang, Yifan Gong

Shared hidden layer combination for speech recognition systems

10/29/15 - 20150310858 - Providing a framework for merging automatic speech recognition (ASR) systems having a shared deep neural network (DNN) feature transformation is provided. A received utterance may be evaluated to generate a DNN-derived feature from the top hidden layer of a DNN. The top hidden layer output may then be utilized to
Inventors: Jinyu Li, Jian Xue, Yifan Gong

Low-footprint adaptation and personalization for a deep neural network

09/10/15 - 20150255061 - The adaptation and personalization of a deep neural network (DNN) model for automatic speech recognition is provided. An utterance which includes speech features for one or more speakers may be received in ASR tasks such as voice search or short message dictation. A decomposition approach may then be applied to
Inventors: Jian Xue, Jinyu Li, Dong Yu, Michael L. Seltzer, Yifan Gong

Restructuring deep neural network acoustic models

12/18/14 - 20140372112 - A Deep Neural Network (DNN) model used in an Automatic Speech Recognition (ASR) system is restructured. A restructured DNN model may include fewer parameters compared to the original DNN model. The restructured DNN model may include a monophone state output layer in addition to the senone output layer of the
Inventors: Jian Xue, Emilian Stoimenov, Jinyu Li, Yifan Gong

Posterior-based feature with partial distance elimination for speech recognition

09/11/14 - 20140257814 - A high-dimensional posterior-based feature with partial distance elimination may be utilized for speech recognition. The log likelihood values of a large number of Gaussians are needed to generate the high-dimensional posterior feature. Gaussians with very small log likelihoods are associated with zero posterior values. Log likelihoods for Gaussians for a
Inventors: Jinyu Li, Zhijie Yan, Qiang Huo, Yifan Gong

Exploiting heterogeneous data in deep neural network-based speech recognition systems

09/11/14 - 20140257804 - Technologies pertaining to training a deep neural network (DNN) for use in a recognition system are described herein. The DNN is trained using heterogeneous data, the heterogeneous data including narrowband signals and wideband signals. The DNN, subsequent to being trained, receives an input signal that can be either a wideband
Inventors: Jinyu Li, Dong Yu, Yifan Gong

Feature space transformation for personalization using generalized i-vector clustering

07/31/14 - 20140214420 - Personalization for Automatic Speech Recognition (ASR) is associated with a particular device. A generalized i-vector clustering method is used to train i-vector parameters on utterances received from a device and to classify test utterances from the same device. A sub-loading matrix and a residual noise term may be used when
Inventors: Kaisheng Yao, Yifan Gong

Adaptive online feature normalization for speech recognition

07/24/14 - 20140207448 - A speech recognition system adaptively estimates a warping factor used to reduce speaker variability. The warping factor is estimated using a small window (e.g. 100 ms) of speech. The warping factor is adaptively adjusted as more speech is obtained until the warping factor converges or a pre-defined maximum number of
Inventors: Shizhen Wang, Yifan Gong, Fileno Alleva

Utilizing scalar operations for recognizing utterances during automatic speech recognition in noisy environments

03/06/14 - 20140067387 - Scalar operations for model adaptation or feature enhancement may be utilized for recognizing an utterance during automatic speech recognition in a noisy environment. An utterance including distorted speech generated from a transmission source for delivery to a receiver, may be received by a computer. The distorted speech may be caused
Inventors: Jinyu Li, Michael Lewis Seltzer, Yifan Gong

Model based online normalization of feature distribution for noise robust speech recognition

03/28/13 - 20130080165 - Online histogram recognition may be provided. Upon receiving a spoken phrase from a user, a histogram/frequency distribution may be estimated on the spoken phrase according to a prior distribution. The histogram distribution may be equalized and then provided to a spoken language understanding application.
Inventors: Shizen Wang, Yifan Gong

Subspace speech adaptation

07/05/12 - 20120173240 - Subspace speech adaptation may be utilized for facilitating the recognition of speech containing short utterances. Speech training data may be received in a speech model by a computer. A first matrix may be determined for preconditioning speech statistics based on the speech training data. A second matrix may be determined
Inventors: Daniel Povey, Kaisheng Yao, Yifan Gong

Online distorted speech estimation within an unscented transformation framework

05/24/12 - 20120130710 - Noise and channel distortion parameters in the vectorized logarithmic or the cepstral domain for an utterance may be estimated, and subsequently the distorted speech parameters in the same domain may be updated using an unscented transformation framework during online automatic speech recognition. An utterance, including speech generated from a transmission
Inventors: Deng Li, Jinyu Li, Dong Yu, Yifan Gong

Model training for automatic speech recognition from imperfect transcription data

12/16/10 - 20100318355 - Techniques and systems for training an acoustic model are described. In an embodiment, a technique for training an acoustic model includes dividing a corpus of training data that includes transcription errors into N parts, and on each part, decoding an utterance with an incremental acoustic model and an incremental language
Inventors: Jinyu Li, Yifan Gong, Chaojun Liu, Kaisheng Yao

Techniques for enhanced automatic speech recognition

09/09/10 - 20100228548 - Techniques for enhanced automatic speech recognition are described. An enhanced ASR system may be operative to generate an error correction function. The error correction function may represent a mapping between a supervised set of parameters and an unsupervised training set of parameters generated using a same set of acoustic training
Inventors: Chaojun Liu, Yifan Gong

Noise suppressor for robust speech recognition

06/17/10 - 20100153104 - Described is noise reduction technology generally for speech input in which a noise-suppression related gain value for the frame is determined based upon a noise level associated with that frame in addition to the signal to noise ratios (SNRs). In one implementation, a noise reduction mechanism is based upon minimum
Inventors: Dong Yu, Li Deng, Yifan Gong, Jian Wu, Alejandro Acero

Phase sensitive model adaptation for noisy speech recognition

03/25/10 - 20100076758 - A speech recognition system described herein includes a receiver component that receives a distorted speech utterance. The speech recognition also includes an updater component that is in communication with a first model and a second model, wherein the updater component automatically updates parameters of the second model based at least
Inventors: Jinyu Li, Li Deng, Dong Yu, Yifan Gong, Alejandro Acero

Adapting a compressed model for use in speech recognition

03/25/10 - 20100076757 - A speech recognition system includes a receiver component that receives a distorted speech utterance. The speech recognition also includes an adaptor component that selectively adapts parameters of a compressed model used to recognize at least a portion of the distorted speech utterance, wherein the adaptor component selectively adapts the parameters
Inventors: Jinyu Li, Li Deng, Dong Yu, Jian Wu, Yifan Gong, Alejandro Acero

Parameter clustering and sharing for variable-parameter hidden markov models

03/18/10 - 20100070280 - A speech recognition system uses Gaussian mixture variable-parameter hidden Markov models (VPHMMs) to recognize speech. The VPHMMs include Gaussian parameters that vary as a function of at least one environmental conditioning parameter. The relationship of each Gaussian parameter to the environmental conditioning parameter(s) is modeled using a piecewise fitting approach,
Inventors: Dong Yu, Li Deng, Yifan Gong, Alejandro Acero

Piecewise-based variable -parameter hidden markov models and the training thereof

03/18/10 - 20100070279 - A speech recognition system uses Gaussian mixture variable-parameter hidden Markov models (VPHMMs) to recognize speech under many different conditions. Each Gaussian mixture component of the VPHMMs is characterized by a mean parameter μ and a variance parameter Σ. Each of these Gaussian parameters varies as a function of at least
Inventors: Dong Yu, Li Deng, Yifan Gong, Alejandro Acero

Model development authoring, generation and execution based on data and processor dependencies

07/09/09 - 20090177471 - A recognition (e.g., speech, handwriting, etc.) model build process that is declarative and data-dependence-based. Process steps are defined in a declarative language as individual processors having input/output data relationships and data dependencies of predecessors and subsequent process steps. A compiler is utilized to generate the model building sequence. The compiler
Inventors: Yifan Gong, Ye Tian

High performance hmm adaptation with joint compensation of additive and convolutive distortions

06/04/09 - 20090144059 - A method of compensating for additive and convolutive distortions applied to a signal indicative of an utterance is discussed. The method includes receiving a signal and initializing noise mean and channel mean vectors. Gaussian dependent matrix and Hidden Markov Model (HMM) parameters are calculated or updated to account for additive
Inventors: Dong Yu, Li Deng, Alejandro Acero, Yifan Gong, Jinyu Li

### Yifan Gong patent invention listings

The bibliographic references displayed about Yifan Gong's patents are for a recent sample of Yifan Gong's publicly published patent applications. The inventor/author may have additional bibliographic citations listed at the is not associated or affiliated in any way with the author/inventor or the United States Patent/Trademark Office but is providing this non-comprehensive sample listing for educational and research purposes using public bibliographic data published and disseminated from the United States Patent/Trademark Office public datafeed. This information is also available for free on the website. If Yifan Gong filed recent patent applications under another name, spelling or location then those applications could be listed on an alternate page. If no bibliographic references are listed here, it is possible there are no recent filings or there is a technical issue with the listing--in that case, we recommend doing a search on the website.


Sign up for the FREE Keyword Monitor and check for keyword phrases (ie. "RFID" , "wireless", "web development", "fuel cells" etc.)...You will be notified when new patent applications and inventions are published that match your keywords. Also you can save for later research public patent/invention documents using our FREE Organizer. It takes only 30 seconds to sign up or login.

Advertise on - Rates & Info

### Support - Terms & Conditions