International Business Machines Corporation

Recycle Go Inc.

Nuance Communications, Inc.

Stanley S Chen

Bhuvana Ramabhadran

Abhinav Sethy

Jan-Robin Gerards

Vaibhava Goel

Samuel Jonathan Thomas

Etienne Marcheret

Lidia Mangu

Kenneth W Church

Laurence P Sansone

Ebru Arisoy

Paul Joseph Vozila

Bowen Zhou

Yuging Gao

David Nahamoo

Michael Alan Picheny

Yuqing Gao

Ramesh Ambat Gopinath

George Andrei Saon

Hong-Kwang Jeff Kuo

Sreeram Viswanath Balakrishnan

Robert L Mercer

Stephen Mingyu Chu

Benoit Maison

Ruhi Sarikaya

Peter F Brown

Stephen A Della Pietra

Vincent J Della Pietra

Geoffrey G Zweig

Maximilian Bisani

Yi Su

Scott Elliot Axelrod

Philip S Resnik

The present disclosure provides a method for facilitating managing of supply chains of items. Further, the method includes receiving supply chain data associated with a supply chain of items from devices. Further, the supply chain includes a transportation of the items. Further, the method includes obtaining additional data based on the supply chain data. Further, the method includes analyzing the additional data using machine learning models based on the supply chain data. Further, the method includes determining a disruption in the supply chain based on the analyzing of the additional data. Further, the method includes generating recommendations for mitigating the disruption in the supply chain based on the disruption. Further, the method includes transmitting the recommendations to the devices. Further, the method includes storing the additional data.

Systems and methods for facilitating managing of supply chains of items

A method to facilitate processing of recyclable items. Accordingly, the method may include capturing, using at least one sensory device, sensory data associated with at least one recyclable item. Further, the method may include receiving, from the at least one sensory device, event data associated with a recycling process. Further, the at least one sensory device may include at least one of a hyperspectral camera, a spectroscopic scanner and a colored filter scanner configured for capturing at least one image of at least one recyclable item undergoing the recycling process. Further, the method may include analyzing, using a processing device, the event data using at least one image processing model. Further, the method may include issuing, using the processing device, the predetermined amount of crypto tokens to a second crypto account associated with a second user device based on the generating and the sensory data.

Methods, systems, apparatuses and devices for facilitating processing of recyclable items

Disclosed herein is a method for facilitating generation of a carbon offset based on processing of a recyclable item. Accordingly, the method may include receiving, using a communication device, transportation data associated with transportation of at least one recyclable item from at least one first device. Further, the method may include analyzing, using a processing device, the transportation data. Further, the method may include determining, using the processing device, a carbon value associated with the transportation of the at least one recyclable item based on the analyzing. Further, the method may include generating, using the processing device, a net COe offset associated with the at least one recyclable item based on the carbon value. Further, the method may include storing, using a storage device, the net COe offset associated with the at least one recyclable item in a distributed ledger.

Systems and methods for facilitating generation of a carbon offset based on processing of a recyclable item

A system to facilitate processing of recyclable items is disclosed. Further, the system may include a communication device configured for receiving event data associated with a recycling process from at least one sensory device, receiving a request for the event data from a first user device, and transmitting the event data to the first user device. Further, the system may include a processing device communicatively coupled to the communication device, configured for issuing a predetermined amount of crypto tokens to a second crypto account. Further, the system may include a storage device communicatively coupled to the processing device, configured for storing, using a distributed ledger technology, the event data, and data related to the issuing of the predetermined amount of crypto tokens to the second crypto account.

A system to facilitate processing of recyclable items is disclosed. Further, the system may include a communication device configured for receiving event data associated with a recycling process from at least one sensory device, receiving a request for the event data from a first user device, and transmitting the event data to the first user device based on deducting of a predetermined amount of crypto tokens from a first crypto account associated with the first user device. Further, the system may include a processing device communicatively coupled to the communication device, configured for deducting the predetermined amount of crypto tokens from the first crypto account. Further, the system may include a storage device communicatively coupled to the processing device, configured for storing, using a distributed ledger technology, the event data, and data related to the deducting of the predetermined amount of crypto tokens from the first crypto account.

A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.

Combining installed audio-visual sensors with ad-hoc mobile audio-visual sensors for smart meeting rooms

Techniques for conversion of non-back-off language models for use in speech decoders. For example, an apparatus for conversion of non-back-off language models for use in speech decoders. For example, an apparatus is configured convert a non-back-off language model to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.

Conversion of non-back-off language models for efficient speech decoding

Some embodiments relate to using an unnormalized neural network language model in connection with a speech processing application. The techniques include obtaining a language segment sequence comprising one or more language segments in a vocabulary; accessing an unnormalized neural network language model having a normalizer node and an output layer comprising a plurality of output nodes, each of the plurality of output nodes associated with a respective language segment in the vocabulary; and determining, using the unnormalized neural network language model, a first likelihood that a first language segment in the vocabulary follows the language segment sequence.

Systems and methods for providing unnormalized language models

Techniques for conversion of non-back-off language models for use in speech decoders. For example, a method comprises the following step. A non-back-off language model is converted to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.

A language processing application employs a classing function optimized for the underlying production application context for which it is expected to process speech. A combination of class based and word based features generates a classing function optimized for a particular production application, meaning that a language model employing the classing function uses word classes having a high likelihood of accurately predicting word sequences encountered by a language model invoked by the production application. The classing function optimizes word classes by aligning the objective of word classing with the underlying language processing task to be performed by the production application. The classing function is optimized to correspond to usage in the production application context using class-based and word-based features by computing a likelihood of a word in an n-gram and a frequency of a word within a class of the n-gram.

Word classing for language modeling

Growing community of inventors

Cambridge, MA, United States of America

Stanley S Chen