Speech recognition apparatus, speech recognition method, and electronic device

SH Yoo, HY Choi - US Patent App. 15/139,926, 2017 - Google Patents
This Summary is provided to introduce a selection of concepts in a simplified form that are
further described below in the Detailed Description. This Summary is not intended to identify …

Speech recognition apparatus and method

HY Choi, H Seok** - US Patent 9,881,615, 2018 - Google Patents
A speech recognition apparatus and method. The speech recognition apparatus includes a
first recognizer configured to generate a first recognition result of an audio signal, in a first …

Regularization techniques for end-to-end speech recognition

Y Zhou, C **ong, R Socher - US Patent App. 15/851,579, 2019 - Google Patents
The disclosed technology teaches regularizing a deep end-to-end speech recognition
model to reduce overfitting and improve generalization: synthesizing sample speech …

Augmented generalized deep learning with special vocabulary

J Ward, A Sypniewski, S Stephenson - US Patent 10,210,860, 2019 - Google Patents
Systems and methods are disclosed for customizing a neural network for a custom dataset,
when the neural network has been trained on data from a general dataset. The neural …

Speech recognition with attention-based recurrent neural networks

W Chan, N Jaitly, QV Le, O Vinyals… - US Patent …, 2017 - Google Patents
Methods, systems, and apparatus, including computer pro grams encoded on computer
storage media for speech rec ognition. One method includes obtaining an input acoustic …

Automatic speech recognition using multi-dimensional models

B Li, TN Sainath - US Patent 9,984,683, 2018 - Google Patents
Methods, systems, and apparatus, including computer programs encoded on a computer
storage medium, for automatic speech recognition using multi-dimensional models. In some …

Training acoustic models using connectionist temporal classification

KK Rao, AW Senior, H Sak - US Patent 10,229,672, 2019 - Google Patents
Methods, systems, and apparatus, including computer pro grams encoded on a computer
storage medium, for training acoustic models and using the trained acoustic models. A …

Systems and methods for queryable graph representations of videos

J Frey, J Whitaker, M Russell - US Patent 9,858,340, 2018 - Google Patents
In one aspect, the present disclosure relates to a method which, in one embodiment,
includes: receiving video data for a first video; deconstructing the video data of the first video …

Enhanced speech generation

E Visser, S Zhang, LH Kim, Y Guo… - US Patent 10,332,520, 2019 - Google Patents
In a particular aspect, an apparatus includes an audio sensor configured to receive an input
audio signal. The apparatus also includes speech generative circuitry configured to …

System and method for detecting generated domain

T Huang, LI Shuaiji, Y Chang, F Zhang… - US Patent 10,764,246, 2020 - Google Patents
A computer-implemented method for domain analysis comprises: obtaining, by a computing
device, a domain; and inputting, by the computing device, the obtained domain to a trained …