Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining the media file with a speech and identifying speakers on clusters separated by disfluencies and change of speakers. Clusters are re-segmented rearranged during diarization. Speaker identifications for the clusters in the media file is produced.

Abstract: A model-pair is selected to recognize spoken words in a speech signal generated from a speech, which includes an acoustic model and a language model. A degree of disjointedness between the acoustic model and the language model is computed relative to the speech by comparing a first recognition output produced from the acoustic model and a second recognition output produced from the language model. When the acoustic model incorrectly recognizes a portion of the speech signal as a first word and the language model correctly recognizes the portion of the speech signal as a second word, a textual representation of the second word is determined and associated with a set of sound descriptors to generate a training speech pattern. Using the training speech pattern, the acoustic model is trained to recognize the portion of the speech signal as the second word.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a media file including a speech by one or more speaker. The language of the speech is identified and biographic data of a speaker of the speech is generated by analyzing semantics and vocal characteristics of the speech. The speaker is diarized and confidence in a resulting speaker label is evaluated against a threshold. The speaker label is adjusted with the language of the speech and biographic data of the speaker and produced as speaker metadata of the media file.

Abstract: Focus data of a remote user is analyzed to determine a focus shift from a first area to a second area at an event arena. A beacon density is computed at the second area, where the beacon density includes a number of physical beacons corresponding to a number of local users at the second area, a number of virtual beacons corresponding to a number of remote users focused on the second area, or a combination of thereof. When the beacon density at the second area exceeds a threshold density, an instruction to a streaming source is generated. The streaming source is caused to change a streaming content, to form changed streaming content that is related to the second area.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting various word data from cross-domain sources and subject websites; assessing relevancy of feature vectors from external domains, live content of subject websites, and secondary terms derived from the live contents; expanding a language model for a domain by relevance passing a logistic regression threshold.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: determining that one or more word of a feature vector more supports than negates a language model corresponding to the domain based on a sensitivity of respective word. Words having acceptable sensitivities are added to the language model, and the language model is enhanced by use of machine learning in order to accurately and comprehensively model the language specific for the domain.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: determining that one or more word of a feature vector more supports than negates a language model corresponding to the domain based on a sensitivity of respective word. Words having acceptable sensitivities are added to the language model, and the language model is enhanced by use of machine learning in order to accurately and comprehensively model the language specific for the domain.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting various word data from cross-domain sources and subject websites; assessing relevancy of feature vectors from external domains, live content of subject websites, and secondary terms derived from the live contents; expanding a language model for a domain by relevance passing a logistic regression threshold.

Abstract: A video stream measurement method and system. The method includes receiving by a computing system, a video stream comprising plurality of timestamps located at specified intervals of the video stream. The computing system broadcasts the video stream for a user and decodes a first time stamp broadcasted during a first time period. The computing system monitors a user interaction function performed by the user and associated with the video stream. The computing system generates and transmits a report comprising a description associated with the user interaction function. The computing system receives an analysis associated with the report.

Abstract: A video stream measurement method and system. The method includes receiving by a computing system, a video stream comprising plurality of timestamps located at specified intervals of the video stream. The computing system broadcasts the video stream for a user and decodes a first time stamp broadcasted during a first time period. The computing system monitors a user interaction function performed by the user and associated with the video stream. The computing system generates and transmits a report comprising a description associated with the user interaction function. The computing system receives an analysis associated with the report.

Abstract: The present invention generally provides a way to analyze crowd noise to identify “highlights” or the like. Specifically, an audio stream containing crowd noise from an event (e.g., sporting event, political rally, religious gathering, etc) is captured (e.g., using microphones) and time coded. The audio stream is normalized based on geography and processed to remove undesired artifacts and to identify a set (at least one) of highlights. Based on at least one threshold, at least one highlight is selected from the set of highlights.

Abstract: A system and associated method for determining web analytics information. A Hypertext Transfer Protocol (HTTP) request for a target page referred from a referring page by a mouse click is processed to calculate web analytics data in the target page. The web analytics data regarding a mouse cursor position, a 2-dimensional information of the target page, and the URL of the referring page is transmitted to a web analytics server to generate the web analytics information for the referring page in format of a heat map of the referring page.

Abstract: An improved solution for accessing a web application is provided. In an embodiment of the invention, a method for controlling access to a web application includes: receiving a request for a first web page application, wherein the first web application is connected to a second web page application via a link at the second web page application; determining if the request is likely from a book marked link to the first web page application or from the link at the second web page application; and providing one of the second web page application and the first web page application based on the determining.

Abstract: A system and associated method for determining web analytics information. A Hypertext Transfer Protocol (HTTP) request for a target page referred from a referring page by a mouse click is processed to calculate web analytics data in the target page. The web analytics data regarding a mouse cursor position, a 2-dimensional information of the target page, and the URL of the referring page is transmitted to a web analytics server to generate the web analytics information for the referring page in format of a heat map of the referring page.

Abstract: The present invention generally provides a way to analyze crowd noise to identify “highlights” or the like. Specifically, an audio stream containing crowd noise from an event (e.g., sporting event, political rally, religious gathering, etc) is captured (e.g., using microphones) and time coded. The audio stream is normalized based on geography and processed to remove undesired artifacts and to identify a set (at least one) of highlights. Based on at least one threshold, at least one highlight is selected from the set of highlights.

Abstract: An improved solution for accessing a web application is provided.