At+t Corp.

Other

AT&T Intellectual Property I, LP

Joel A Winthrop

Kenneth H Rosen

Robert Edward Markowitz

Sanjay Agraharam

David Hilton Shur

Randy Glen Goldberg

Richard M Sachs

An apparatus and method for the robust recognition of speech during a call in a noisy environment is presented. Specific background noise models are created to model various background noises which may interfere in the error free recognition of speech. These background noise models are then used to determine which noise characteristics a particular call has. Once a determination has been made of the background noise in any given call, speech recognition is carried out using the appropriate background noise model.

Selective noise/channel/coding models and recognizers for automatic speech recognition

A method and apparatus that enhances a multicast information stream, such as an IP multicast session, in a communication network is provided. The stream is received through the communication network and is enhanced at substantially the time the first stream is received. The information stream may be enhanced by adding transcribed content, such as content generated by speech recognition software, or translated content, such as from a first language to a second language, to the stream. The information stream may also be enhanced by adding content to the first information stream, such as content is related to the original content. The enhanced stream may be sent to a user as a second multicast information stream. The enhanced stream may be received by the user in place of, or along with, the original information stream. The enhanced content may be sent to the user at the conclusion of the information stream, if desired.

Method and apparatus to enhance a multicast information stream in a communication network

The present invention provides an apparatus and method for conducting a video conference. The video conference apparatus is connected to at least one network. The video conference apparatus includes a MCU, an environment processor, a user database interface and an environment database interface. When users log onto the video conference apparatus, it is determined whether each user has designated an alternative environment from that normally detected by the camera device during the video conference. If the user has designated an alternative environment, the environment processor obtains the environment from the environment database and the video conference apparatus uses the designated environment during the video conference. However, if the user has not designated an alternative environment, the environment processor sends a request message providing a listing of possible environments which may be used during the video conference. Thus, the user may select a desired environment from the listing and use it during the video conference. If the user does not wish to select an alternative environment, a default environment corresponding to the environment normally detected through the camera device is used during the video conference.

Apparatus and method for incorporating virtual video conferencing environments

A method and apparatus that enhances a multicast information stream, such as an IP multicast session, in a communication network is provided. The stream is received through the communication network and is enhanced at substantially the time the first stream is received. The information stream may be enhanced by adding transcribed content, such as content generated by speech recognition software, or translated content, such as from a first language to a second language, to the stream. The information stream may also be enhanced by adding content to the first information stream, such as content related to the original content. The enhanced stream may be sent to a user as a second multicast information stream. The enhanced stream may be received by the user in place of, or along with, the original information stream. The enhanced content may be sent to the user at the conclusion of the information stream, if desired.

A network based platform uses face recognition, speech recognition, background change detection and key scene events to index multimedia communications. Before the multimedia communication begins, active participants register their speech and face models with a server. The process consists of creating a speech sample, capturing a sample image of the participant and storing the data in a database. The server provides an indexing function for the multimedia communication. During the multimedia communication, metadata including time stamping is retained along with the multimedia content. The time stamping information is used for synchronizing the multimedia elements. The multimedia communication is then processed through the server to identify the multimedia communication participants based on speaker and face recognition models. This allows the server to create an index table that becomes an index of the multimedia communication. In addition, through scene change detection and background recognition, certain backgrounds and key scene information can be used for indexing. Therefore, through this indexing apparatus and method, a specific participant can be recognized as speaking and the content that the participant discussed can also be used for indexing.

Growing community of inventors

Little Silver, NJ, United States of America

Joel A Winthrop