Abstract: Implementations relate to verifying labels for images using image recognition. In some implementations, a method includes obtaining an image associated with location information, obtaining one or more descriptor labels associated with the location information, determining one or more recognized image features depicted in the image, comparing the recognized image features with the descriptor labels, and determining one or more verified labels from the one or more descriptor labels. The verified labels are determined to describe at least one of the one or more recognized image features depicted in the image based on the comparing of the recognized image features with the descriptor labels.

Abstract: A media content distribution system includes a portable device operable to store media content, wirelessly receive input signals, select a portion of the media content based on the input signals, and communicate the selected portion to a user. The system further includes a signaling mechanism disposed at a location and producing an input signal in a range respective to the location. The input signal is selected to ensure that the selected portion of media content includes information relating to the location when the portable device is disposed within the range.

Abstract: The vehicular monitoring system obtains audio information from the speech of occupants within the vehicle and then processes that audio information to extract information about the behavior of the vehicle occupants. Using the behavioral information the system then assesses whether said behavior is in compliance with a predefined set of rules. Severe violations are reported to a third party via cellular telephone or other means. Less severe violations are recorded in a log file that is subsequently uploaded to a networked computer system for review and analysis. The behavioral rules used to assess violations may be modified by the administrative user.

Abstract: A personal item monitoring system includes a monitor having a transmitter and a receiver located therein. At least one radio identification tag is adapted to be coupled to a personal item. Alternatively, the radio identification tag may be pre-installed into the personal item. The monitor emits a radio frequency received by the radio frequency identification tag, and the radio frequency identification tag emits a responding signal if within a detection range. The monitor then alerts a user if the radio identification tag leaves the range of detection.

Abstract: A method and apparatus for data entry by voice under adverse conditions is disclosed. More specifically it provides a way for efficient and robust form filling by voice. A form can typically contain one or several fields that must be filled in. The user communicates to a speech recognition system and word spotting is performed upon the utterance. The spotted words of an utterance form a phrase that can contain field-specific values and/or commands. Recognized values are echoed back to the speaker via a text-to-speech system. Unreliable or unsafe inputs for which the confidence measure is found to be low (e.g. ill-pronounced speech or noises) are rejected by the spotter. Speaker adaptation is furthermore performed transparently to improve speech recognition accuracy. Other input modalities can be additionally supported (e.g. keyboard and touch-screen). The system maintains a dialogue history to enable editing and correction operations on all active fields.

Abstract: A common requirement in automatic speech recognition is to recognize a set of words for any speaker without training the system for each new speaker. A speech recognition system is provided utilizing linear discriminant based phonetic similarities with inter-phonetic unit value normalization. Linear discriminant analysis is utilized using training data with both in-class and out-class sample training utterances for generating linear discriminant vectors for each of the phonetic units. The dot product of each linear discriminant vector and the time spectral pattern vectors generated from the input speech are computed. The resultant raw similarity vectors are then normalized utilizing normalization look-up tables for providing similarity vectors which are utilized by a word matcher for word recognition.

Abstract: A media content distribution system includes a portable device operable to store media content, wirelessly receive input signals, select a portion of the media content based on the input signals, and communicate the selected portion to a user. The system further includes a signaling mechanism disposed at a location and producing an input signal in a range respective to the location. The input signal is selected to ensure that the selected portion of media content includes information relating to the location when the portable device is disposed within the range.

Abstract: The call screener employs a telephone system interface connected between a telephone network and a telephone device of a user. The interface selectively routes calls (and refrain from routing calls) based on the results from the dialogue system. The dialogue system elicits speech from an incoming caller and causes the telephone system interface to route calls from the incoming caller based on a comparison of the elicited speech with a set of stored speaker models. The stored speaker models may be maintained automatically by the system, using either a passive mode, in which calls exceeding a predetermined duration are assumed to be “acceptable” callers; and a proactive mode in which the system prompts the user at the end of the call to elect whether to save the speech models developed during that call in the acceptable user database.

Abstract: The call screener employs a telephone system interface connected between a telephone network and a telephone device of a user. The interface selectively routes calls (and refrain from routing calls) based on the results from the dialogue system. The dialogue system elicits speech from an incoming caller and causes the telephone system interface to route calls from the incoming caller based on a comparison of the elicited speech with a set of stored speaker models. The stored speaker models may be maintained automatically by the system, using either a passive mode, in which calls exceeding a predetermined duration are assumed to be “acceptable” callers; and a proactive mode in which the system prompts the user at the end of the call to elect whether to save the speech models developed during that call in the acceptable user database.

Abstract: A method and apparatus for data entry by voice under adverse conditions is disclosed. More specifically it provides a way for efficient and robust form filling by voice. A form can typically contain one or several fields that must be filled in. The user communicates to a speech recognition system and word spotting is performed upon the utterance. The spotted words of an utterance form a phrase that can contain field-specific values and/or commands. Recognized values are echoed back to the speaker via a text-to-speech system. Unreliable or unsafe inputs for which the confidence measure is found to be low (e.g. ill-pronounced speech or noises) are rejected by the spotter. Speaker adaptation is furthermore performed transparently to improve speech recognition accuracy. Other input modalities can be additionally supported (e.g. keyboard and touch-screen). The system maintains a dialogue history to enable editing and correction operations on all active fields.

Abstract: A common requirement in automatic speech recognition is to recognize a set of words for any speaker without training the system for each new speaker. A speech recognition system is provided utilizing linear discriminant based phonetic similarities with inter-phonetic unit value normalization. Linear discriminant analysis is utilized using training data with both in-class and out-class sample training utterances for generating linear discriminant vectors for each of the phonetic units. The dot product of each linear discriminant vector and the time spectral pattern vectors generated from the input speech are computed. The resultant raw similarity vectors are then normalized utilizing normalization look-up tables for providing similarity vectors which are utilized by a word matcher for word recognition.