Binary and multi-class classification systems and methods using connectionist temporal classification
SM Kaskari, T Thormundsson, F Nesta - US Patent 10,762,891, 2020 - Google Patents
A classification training system for binary and multi-class classification comprises a neural
network operable to perform classification of input data, a training dataset including pre …
network operable to perform classification of input data, a training dataset including pre …
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 …
Processing sequences using convolutional neural networks
Methods, systems, and apparatus, including computer programs encoded on computer
storage media, for processing sequences using convolutional neural networks. One of the …
storage media, for processing sequences using convolutional neural networks. One of the …
Device text to speech
Systems and processes for generating speech from text are provided. An example method of
generating speech from text includes, at an electronic device having at least one processor …
generating speech from text includes, at an electronic device having at least one processor …
Tool for facilitating efficiency in machine learning
R Barik, BT Lewis, M Sundaresan, J Jackson… - US Patent …, 2022 - Google Patents
A mechanism is described for facilitating smart distribution of resources for deep learning
autonomous machines. A method of embodiments, as described herein, includes detecting …
autonomous machines. A method of embodiments, as described herein, includes detecting …
Method and system for training neural sequence-to-sequence models by incorporating global features
Neural sequence-to-sequence (seq2seq) models are useful in various applications that
involve producing one or more output sequences from one or more input sequences …
involve producing one or more output sequences from one or more input sequences …
Multi-modal interfaces having selection disambiguation and text modification capability
TR Gruber, MA Tayyeb, RC Santos… - US Patent …, 2024 - Google Patents
Abstract Systems and processes for operating an intelligent automated assistant to perform
intelligent list reading are provided. In accordance with one example, a method includes, at …
intelligent list reading are provided. In accordance with one example, a method includes, at …
Speech recognition using convolutional neural networks
Methods, systems, and apparatus, including computer programs encoded on computer
storage media, for performing speech recognition by generating a neural network output …
storage media, for performing speech recognition by generating a neural network output …
Intelligent device identification
BJ Newendorp, LT Napolitano - US Patent 12,051,413, 2024 - Google Patents
Abstract Systems and processes for intelligent device identification are provided. In one
example process, audio input may be sampled with a microphone at each of two or more of …
example process, audio input may be sampled with a microphone at each of two or more of …
End-to-end neural networks for speech recognition and classification
A Sypniewski, J Ward, S Stephenson - US Patent 10,720,151, 2020 - Google Patents
Abstract Systems and methods are disclosed for end-to-end neural networks for speech
recognition and classification and additional machine learning techniques that may be used …
recognition and classification and additional machine learning techniques that may be used …