Abstract: Provided are techniques for domain specific correction of output from automatic speech recognition. An output of an automatic speech recognition engine is received. An alphanumeric sequence is extracted from the output, where the alphanumeric sequence represents an erroneous translation by the automatic speech recognition engine. Candidates for the alphanumeric sequence are generated. The candidates are ranked based on scores associated with the candidates. A candidate of the candidates having a highest score of the scores is selected. The output is corrected by replacing the alphanumeric sequence with the selected candidate. The corrected output is returned.

Abstract: Using a computing device to convert verbal communications including non-standard speech to text. The computing device receives an audio recording of voice and generates a standard text log. A standard word dictionary is retrieved. Non-standard words not found in the word dictionary are determined. Portions of the audio recording corresponding to the non-standard words are retrieved. Portions of the audio recording corresponding to non-standard words into input into a natural language understanding model. The computing device utilizes the results of the natural language understanding model to determine a best-match non-standard dictionary. One or more portions of the audio recording are used to generate a non-standard text log. The standard text log and non-standard text log are merged.

Abstract: Provided are techniques for domain specific correction of output from automatic speech recognition. An output of an automatic speech recognition engine is received. An alphanumeric sequence is extracted from the output, where the alphanumeric sequence represents an erroneous translation by the automatic speech recognition engine. Candidates for the alphanumeric sequence are generated. The candidates are ranked based on scores associated with the candidates. A candidate of the candidates having a highest score of the scores is selected. The output is corrected by replacing the alphanumeric sequence with the selected candidate. The corrected output is returned.

Abstract: Using a computing device to convert verbal communications including non-standard speech to text. The computing device receives an audio recording of voice and generates a standard text log. A standard word dictionary is retrieved. Non-standard words not found in the word dictionary are determined. Portions of the audio recording corresponding to the non-standard words are retrieved. Portions of the audio recording corresponding to non-standard words into input into a natural language understanding model. The computing device utilizes the results of the natural language understanding model to determine a best-match non-standard dictionary. One or more portions of the audio recording are used to generate a non-standard text log. The standard text log and non-standard text log are merged.

Abstract: One or more processors determine whether a hazard that is detected by a first mobile device exists based on data received from at least one second mobile device. The second mobile device is within a proximity to the first mobile device, which is determined based on a type of the hazard. One or more processors respond to a determination that the hazard does exist by determining a course of action. The course of action is configured for a user based on at least one attribute of the user. One or more processors send the course of action to the first mobile device.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for catalog digitization. A method including receiving observed information including physical attributes of a plurality of products, assigning an importance to each physical attribute, organizing the products into product categories based on the physical attributes and their corresponding importance, determining a product profile for of the products based on the product category of each of the products and a likelihood of any two attributes being observed together with respect to each of the products, identifying a match between two products based on a similarity between the physical attributes of the two products and their corresponding importance, and a comparison between the product profiles of the two products, preparing a product description based on a combination of the physical attributes of the two matching products, and creating a digital product catalog comprising the product description.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for catalog digitization. A method including receiving observed information including physical attributes of a plurality of products, assigning an importance to each physical attribute, organizing the products into product categories based on the physical attributes and their corresponding importance, determining a product profile for of the products based on the product category of each of the products and a likelihood of any two attributes being observed together with respect to each of the products, identifying a match between two products based on a similarity between the physical attributes of the two products and their corresponding importance, and a comparison between the product profiles of the two products, preparing a product description based on a combination of the physical attributes of the two matching products, and creating a digital product catalog comprising the product description.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for catalog digitization. A method including receiving observed information including physical attributes of a plurality of products, assigning an importance to each physical attribute, organizing the products into product categories based on the physical attributes and their corresponding importance, determining a product profile for of the products based on the product category of each of the products and a likelihood of any two attributes being observed together with respect to each of the products, identifying a match between two products based on a similarity between the physical attributes of the two products and their corresponding importance, and a comparison between the product profiles of the two products, preparing a product description based on a combination of the physical attributes of the two matching products, and creating a digital product catalog comprising the product description.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for catalog digitization. A method including receiving observed information including physical attributes of a plurality of products, assigning an importance to each physical attribute, organizing the products into product categories based on the physical attributes and their corresponding importance, determining a product profile for of the products based on the product category of each of the products and a likelihood of any two attributes being observed together with respect to each of the products, identifying a match between two products based on a similarity between the physical attributes of the two products and their corresponding importance, and a comparison between the product profiles of the two products, preparing a product description based on a combination of the physical attributes of the two matching products, and creating a digital product catalog comprising the product description.

Abstract: The flow of a fluid such as water is controlled through an outlet by detecting sound within an environment at a first time and generating a first profile based upon the content of the sound detected at the first time. The flow of the fluid is further controlled by detecting sound within the environment at a second time and generating a second profile based upon the content of the sound detected at the second time. The flow of the fluid is still further controlled by comparing the second profile with the first profile and controlling a control valve to shut off a supply of the fluid exiting a tap based upon the results of the comparison.

Abstract: One or more processors determine whether a hazard that is detected by a first mobile device exists based on data received from at least one second mobile device. The second mobile device is within a proximity to the first mobile device, which is determined based on a type of the hazard. One or more processors respond to a determination that the hazard does exist by determining a course of action. The course of action is configured for a user based on at least one attribute of the user. One or more processors send the course of action to the first mobile device.

Abstract: A method, system and computer program product for performing cache sharing of enterprise data among peer mobile devices. An enterprise server receives a request from a mobile device for enterprise data. Upon identifying peer mobile device(s) that store the requested enterprise data, the enterprise server selects one of these peer mobile devices to provide the requested enterprise data based on an algorithm. A message is sent to the selected peer mobile device from the enterprise server to provide the requested enterprise data to the requesting mobile device, where the message includes connection details as well as a key that uniquely identifies the requested enterprise data that is stored in a cache of the peer mobile device. In this manner, the enterprise data may be shared in a robust and transparent manner while at the same time providing the enterprise control over the dissemination of the enterprise data.

Abstract: A mechanism is provided for leasing fragmented storage between processes. The mechanism comprises a fragmented memory manager associated with instances of virtual memory managers to provide a pool of memory that may lease from the owners of the memory and in turn sub-let the memory for use by other processes or owners. The mechanism allows programs to operate under normal conditions until fragmentation sets. A different memory manager leases those fragmented memory blocks from processes to create a virtually contiguous block of memory that it can sub-lease to processes in need of temporary expansion beyond the memory available for the processes under normal circumstances.

Abstract: A method, system and computer program product for performing cache sharing of enterprise data among peer mobile devices. An enterprise server receives a request from a mobile device for enterprise data. Upon identifying peer mobile device(s) that store the requested enterprise data, the enterprise server selects one of these peer mobile devices to provide the requested enterprise data based on an algorithm. A message is sent to the selected peer mobile device from the enterprise server to provide the requested enterprise data to the requesting mobile device, where the message includes connection details as well as a key that uniquely identifies the requested enterprise data that is stored in a cache of the peer mobile device. In this manner, the enterprise data may be shared in a robust and transparent manner while at the same time providing the enterprise control over the dissemination of the enterprise data.

Abstract: A mechanism is provided for leasing fragmented storage between processes. The mechanism comprises a fragmented memory manager associated with instances of virtual memory managers to provide a pool of memory that may lease from the owners of the memory and in turn sub-let the memory for use by other processes or owners. The mechanism allows programs to operate under normal conditions until fragmentation sets. A different memory manager leases those fragmented memory blocks from processes to create a virtually contiguous block of memory that it can sub-lease to processes in need of temporary expansion beyond the memory available for the processes under normal circumstances.