Training speech recognition systems using word sequences
D Thomson, J Adams, K Boehme - US Patent 10,388,272, 2019 - Google Patents
A method may include obtaining first audio data of a communication session between a first
device and a second device, obtaining a text string that is a transcription of the first audio …
device and a second device, obtaining a text string that is a transcription of the first audio …
Transcription generation from multiple speech recognition systems
2018-12-06 Assigned to CAPTIONCALL, LLC reassignment CAPTIONCALL, LLC
ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors …
ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors …
Training of speech recognition systems
D Thomson, J Adams - US Patent 11,170,761, 2021 - Google Patents
A method may include obtaining first audio data of a first communication session between a
first and second device and during the first communication session, obtaining a first text …
first and second device and during the first communication session, obtaining a first text …
Training speech recognition systems using word sequences
D Thomson, J Adams, K Boehme - US Patent 10,672,383, 2020 - Google Patents
A method may include obtaining first audio data of a communication session between a first
device and a second device, obtaining a text string that is a transcription of the first audio …
device and a second device, obtaining a text string that is a transcription of the first audio …
Regularization techniques for end-to-end speech recognition
The disclosed technology teaches regularizing a deep end-to-end speech recognition
model to reduce overfitting and improve generalization: synthesizing sample speech …
model to reduce overfitting and improve generalization: synthesizing sample speech …
End-to-end speech recognition with policy learning
The disclosed technology teaches a deep end-to-end speech recognition model, including
using multi-objective learning criteria to train a deep end-to-end speech recognition model …
using multi-objective learning criteria to train a deep end-to-end speech recognition model …
Hierarchical and interpretable skill acquisition in multi-task reinforcement learning
US11562287B2 - Hierarchical and interpretable skill acquisition in multi-task reinforcement
learning - Google Patents US11562287B2 - Hierarchical and interpretable skill acquisition in …
learning - Google Patents US11562287B2 - Hierarchical and interpretable skill acquisition in …
Convolutional recurrent neural networks for small-footprint keyword spotting
Described herein are systems and methods for creating and using Convolutional Recurrent
Neural Networks (CRNNs) for small-footprint keyword spotting (KWS) systems. Inspired by …
Neural Networks (CRNNs) for small-footprint keyword spotting (KWS) systems. Inspired by …
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 …
when the neural network has been trained on data from a general dataset. The neural …
Systems and methods for multi-speaker neural text-to-speech
Described herein are systems and methods for augmenting neural speech synthesis
networks with low-dimensional trainable speaker embeddings in order to generate speech …
networks with low-dimensional trainable speaker embeddings in order to generate speech …