Evaluating transcriptions with a semantic parser

PJM Mengibar, F Biadsy, DM Casado - US Patent 8,868,409, 2014 - Google Patents
In some implementations, audio data for an utterance is provided over a network. At a client
device and over the network, information is received that indicates candidate transcriptions …

Graph long short term memory for syntactic relationship discovery

CB Quirk, KN Toutanova, W Yih, H Poon… - US Patent …, 2019 - Google Patents
Long short term memory units that accept a non-predefined number of inputs are used to
provide natural language relation extraction over a user-specified range on content. Content …

Word-level correction of speech input

MJ Lebeau, WJ Byrne, JN Jitkoff, BM Ballinger… - US Patent …, 2018 - Google Patents
The subject matter of this specification can be implemented in, among other things, a
computer-implemented method for correcting words in transcribed text including receiving …

Continuous block tracking for temporal prediction in video encoding

DP Kottke, JJ Guo, LEE Jeyun, S Park, C Weed… - US Patent …, 2017 - Google Patents
(60) Provisional application No. 61/950,784, filed on Mar. tions over reference frames to
produce better inter-predic 10, 2014, provisional application No. 62/049.342, tions than …

Feature-based hybrid video codec comparing compression efficiency of encodings

CP Pace - US Patent 8,942,283, 2015 - Google Patents
Systems and methods of processing video data are provided. Video data having a series of
video frames is received and processed. One or more instances of a candidate feature are …

Video compression repository and model reuse

CP Pace, D DeForest, N Lee, R Pizzorni… - US Patent …, 2014 - Google Patents
(51) Int. Cl stream is applied to video data having a series of video tion 72 6(2006.01)
frames. Computer-vision-based feature and object detection H04N 9/19(201 4.015 …

Perceptual optimization for model-based video encoding

N Lee, S Park, M Tun, DP Kottke, LEE Jeyun… - US Patent …, 2018 - Google Patents
Perceptual statistics are used to compute importance maps that indicate which regions of a
video frame are important to the human visual system. Importance maps may be generated …

Automatic segmentation of video

G Ambwani, AR Davis - US Patent 8,423,555, 2013 - Google Patents
US PATENT DOCUMENTS 4,227,177 A 10, 1980 Moshier 5,493,677 A 2/1996 Balogh et al.
5,521,841 A 5, 1996 Arman et al. 5,530,859 A 6/1996 Tobias, II et al. 5.535, 063 A 7, 1996 …

Perceptual optimization for model-based video encoding

N Lee, S Park, M Tun, DP Kottke, LEE Jeyun… - US Patent …, 2018 - Google Patents
Perceptual statistics may be used to compute importance maps that indicate which regions
of a video frame are important to the human visual system. Importance maps may be applied …

Computer method and apparatus for processing image data

CP Pace - US Patent 8,908,766, 2014 - Google Patents
A method and apparatus for image data compression includes detecting a portion of an
image signal that uses a disproportionate amount of bandwidth compared to other portions …