Kyu Sung Han

20040083930, May 6, 2004

Aug 18, 2003

10/404165

Kyu Han - Santa Clara CA, US

A47B023/00

108/044000

A method and associated apparatus of mounting an object such as a portable computer on a vehicle steering wheel provides an ergonomic workstation environment in a vehicle and an optimal operation environment for the object. In a preferred embodiment, representatively incorporated as a vehicle steering wheel mounted workstation apparatus, the mounting method comprises of a proximal hanging member with elongated opening over the upper part of the steering wheel, at least two distal lower corner holders for holding the object in an inclined position over the frontal area of the steering wheel, an optional standoff under the apparatus for clearance and stability from possible protrusion existing on the steering wheel, a ventilation opening for an unrestricted air flow, and a wrist rest for ergonomics. The mountable object is not limited to but includes any objects such a; portable processing devices of computation, entertainment, communication, or measurement as well as books and binders.

20220383858, Dec 1, 2022

Oct 4, 2021

17/493716

- New York NY, US
Kwangyoun Kim - Santa Clara CA, US
Jing Pan - San Jose CA, US
Kyu Jeong Han - Pleasanton CA, US
Kilian Quirin Weinberger - Ithaca NY, US
Yoav Artzi - New York NY, US

G10L 15/16
G10L 15/183

For any application that processes speech, improving the quality of the feature vectors may improve the quality of the speech application. The quality of feature vectors may be improved by modifying a neural network architecture for computing feature vectors to allocate computational resources where they are more effective for learning and computing the feature vectors. Contextual feature vectors may be computed from feature vectors by using a parameterized downsampling operation that decreases a vector sequence rate, processing the downsampled vectors with a neural network, and using a parameterized upsampling operation that increases a vector sequence rate. For example, parameterized downsampling may decrease a vector sequence rate by a factor of two, a neural may require fewer computational resources since it operates with a lower vector sequence rate, and parameterized upsampling may then increase the vector sequence rate by a factor of two.

20220319501, Oct 6, 2022

Nov 18, 2021

17/530139

- New York NY, US
Felix Wu - Ithaca NY, US
Prashant Sridhar - New York NY, US
Kyu Jeong Han - Pleasanton CA, US

G10L 15/16
G06N 3/04
G10L 15/26

The amount of future context used in a speech processing application allows for tradeoffs between performance and the delay in providing results to users. Existing speech processing applications may be trained with a specified future context size and perform poorly when used in production with a different future context size. A speech processing application trained using a stochastic future context allows a trained neural network to be used in production with different amounts of future context. During an update step in training, a future-context size may be sampled from a probability distribution, used to mask a neural network, and compute an output of the masked neural network. The output may then be used to compute a loss value and update parameters of the neural network. The trained neural network may then be used in production with different amounts of future context to provide greater flexibility for production speech processing applications.

20180032902, Feb 1, 2018

Jul 27, 2016

15/221483

- Dearborn MI, US
Kyu Jeong Han - Palo Alto CA, US
Francois Charette - Tracy CA, US
Gintaras Vincent Puskorius - Novi MI, US

G06N 99/00
G06N 3/08
G06F 17/30

Training tuples including text and a question and answer corresponding to the text are input to a machine learning algorithm, such as a deep neural network. A Q&A model is obtained that outputs questions and answers given an input text. The training tuples may be obtained from standardized test such that the text is a question prompt and the questions and answers are based on the prompt. Raw text is input to the Q&A model to obtain second training tuples including a question and an answer. An NLU model is trained according to the second training tuples. The NLU model may then be installed on a consumer device, which will then use the model to respond to conversational queries and provide an appropriate response.

20170364776, Dec 21, 2017

Jun 15, 2016

15/183610

- Dearborn MI, US
Jinesh J. Jain - Palo Alto CA, US
Kyu Jeong Han - Palo Alto CA, US
Harpreetsingh Banvait - Sunnyvale CA, US

G06K 9/66
G06F 17/50
G01S 17/00
G01S 13/00
G01S 13/93
G01S 13/86
G06N 99/00
G01S 17/93

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a parked vehicle with its engine running. The location of the parked vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of the parked vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a parked vehicle with its engine running based on actual sensor outputs input to the machine learning model.

20170113684, Apr 27, 2017

Oct 27, 2015

14/924187

- Dearborn MI, US
Kyu Jeong Han - Palo Alto CA, US
Jinesh J. Jain - San Mateo CA, US

B60W 30/09
H04L 29/08

A controller for an autonomous vehicle receives audio signals from one or more microphones. The outputs of the microphones are pre-processed to enhance audio features that originated from vehicles. The outputs may also be processed to remove noise. The audio features are input to a machine learning model that classifies the source of the audio features. For example, features may be classified as originating from a vehicle. A direction to a source of the audio features is determined based on relative delays of the audio features in signals from multiple microphones. Where audio features are classified with an above-threshold confidence as originating from a vehicle, collision avoidance is performed with respect to the direction to the source of the audio features.