公开(公告)号：US20230290340A1

公开(公告)日：2023-09-14

申请号：US18118619

申请日：2023-03-07

Applicant: Accenture Global Solutions Limited

Inventor： Lavinia Andreea Danielescu ,  Kenneth Michael Stewart ,  Noah Gideon Pacik-Nelson ,  Timothy M. Shea

IPC: G10L15/16 ,  G10L21/013 ,  G10L25/24

CPC classification number: G10L15/16 ,  G10L21/013 ,  G10L25/24

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for converting audio to spikes for input to a spiking neural network configured to recognize speech based on the spikes are described. In some aspects, a method includes obtaining audio data and generating frequency domain audio signals that represent the audio data by converting the audio data into a frequency domain. The frequency domain audio signals are mapped into a set of Mel-frequency bands to obtain Mel-scale frequency audio signals. A log transformation is performed on the Mel-scale frequency audio signals to obtain log-Mel signals. Spike input is generated for input to a spiking neural network (SNN) model by converting the log-Mel signals to the series of spikes. The spike input is provided as an input to the SNN model.

公开(公告)号：US20240391267A1

公开(公告)日：2024-11-28

申请号：US18321955

申请日：2023-05-23

Applicant: Accenture Global Solutions Limited

Inventor： Noah Gideon Pacik-Nelson ,  Aditi Maheshwari

IPC: B41J29/393 ,  B41J2/32 ,  B41J2/47

Abstract: An automated system and method of printing designs. The system and method can manage print content by application of programmable inks to selected areas in the packaging where frequently modified designs are printed. Such an approach allows the area to be precisely activated to correspond to the target pattern of the desired design and permanently change color. In some embodiments, any change in the text on the packaging/label would then only need to be translated into a corresponding UV or heat pattern, thereby avoiding the production of a new print cylinder to print the changed design. The proposed embodiments are effective in reducing downtime during print operations as well as expanding the capacity of the print apparatus to dynamically respond to changes in print designs.

公开(公告)号：US20240096313A1

公开(公告)日：2024-03-21

申请号：US17946523

申请日：2022-09-16

Applicant: Accenture Global Solutions Limited

Inventor： Lavinia Andreea Danielescu ,  Timothy M. Shea ,  Kenneth Michael Stewart ,  Noah Gideon Pacik-Nelson ,  Eric Michael Gallo

IPC: G10L15/16 ,  G10L15/06 ,  G10L15/197 ,  G10L15/22 ,  G10L15/30 ,  G10L25/21

CPC classification number: G10L15/16 ,  G10L15/063 ,  G10L15/197 ,  G10L15/22 ,  G10L15/30 ,  G10L25/21 ,  G10L2015/0635 ,  G10L2015/223

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing speech using a spiking neural network acoustic model implemented on a neuromorphic processor are described. In one aspect, a method includes receiving, a trained acoustic model implemented as a spiking neural network (SNN) on a neuromorphic processor of a client device, a set of feature coefficients that represent acoustic energy of input audio received from a microphone communicably coupled to the client device. The acoustic model is trained to predict speech sounds based on input feature coefficients. The acoustic model generates output data indicating predicted speech sounds corresponding to the set of feature coefficients that represent the input audio received from the microphone. The neuromorphic processor updates one or more parameters of the acoustic model using one or more learning rules and the predicted speech sounds of the output data.

公开(公告)号：US12142263B2

公开(公告)日：2024-11-12

申请号：US17946523

申请日：2022-09-16

Applicant: Accenture Global Solutions Limited

Inventor： Lavinia Andreea Danielescu ,  Timothy M. Shea ,  Kenneth Michael Stewart ,  Noah Gideon Pacik-Nelson ,  Eric Michael Gallo

IPC: G10L15/16 ,  G10L15/06 ,  G10L15/197 ,  G10L15/22 ,  G10L15/30 ,  G10L25/21

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing speech using a spiking neural network acoustic model implemented on a neuromorphic processor are described. In one aspect, a method includes receiving, a trained acoustic model implemented as a spiking neural network (SNN) on a neuromorphic processor of a client device, a set of feature coefficients that represent acoustic energy of input audio received from a microphone communicably coupled to the client device. The acoustic model is trained to predict speech sounds based on input feature coefficients. The acoustic model generates output data indicating predicted speech sounds corresponding to the set of feature coefficients that represent the input audio received from the microphone. The neuromorphic processor updates one or more parameters of the acoustic model using one or more learning rules and the predicted speech sounds of the output data.

公开(公告)号：US20230262886A1

公开(公告)日：2023-08-17

申请号：US18105454

申请日：2023-02-03

Applicant: Accenture Global Solutions Limited

Inventor： Mark Benjamin Greenspan ,  Taylor Tabb ,  Noah Gideon Pacik-Nelson ,  Eric Michael Gallo ,  Lavinia Andreea Danielescu

IPC: H05K1/02 ,  H05K1/11 ,  H05K3/30 ,  H05K1/18

CPC classification number: H05K1/0296 ,  H05K1/0278 ,  H05K1/115 ,  H05K3/30 ,  H05K1/18 ,  B33Y80/00

Abstract: Electrical input devices, conductive traces, and microcontroller interface devices can be created in a single print using a multi-material 3D printing process. The devices can include a non-conductive material portion and a conductive material portion. The non-conductive and conductive material portions are integrally formed during a single 3D printing process. For example, a fully functional QWERTY keyboard, ready to receive a microcontroller, can be multi-material 3D printed using the techniques described herein.