An audio fingerprint is extracted from an audio sample, where the fingerprint contains information that is characteristic of the content in the sample. The fingerprint may be generated by computing an energy spectrum for the audio sample, resampling the energy spectrum logarithmically in the time dimension, transforming the resampled energy spectrum to produce a series of feature vectors, and computing the fingerprint using differential coding of the feature vectors. The generated fingerprint ca...

A method and system for building/updating grammars in voice access systems is disclosed. The method includes receiving a grammar update request from a voice access system, retrieving data, filtering the data and providing the filtered data to the voice access system. The grammar update request identifies a navigation context of a user interface provided by a data system. The user interface provides access to information in the data system. The data is retrieved from the data system and pertains ...

Conversations that take place over an electronically recordable channel are analyzed by constructing a set of features from the speech of two participants in the conversation. The set of features is applied to a model or a plurality of models to determine the likelihood of the set of features for each model. These likelihoods are then used to classify the conversation into categories, provide real-time monitoring of the conversation, and/or identify anomalous conversations.

This invention is a combination of software and hardware components and methodologies that enable voice recognition for multiple users simultaneously. It introduces the concept of a "conversational voice log" and how voice logs are combined to represent the spoken words of a meeting or group conversations. It defines the components needed, command set for control, text output features, and usage of such a system.

A method and apparatus for allowing a user device to avoid undesired state transitions when the user is present but not performing activities is provided. The method provides for detection of activity in the proximity of the user device by monitoring for sounds via an audio input device connected to the user device. The method further provides for analysis of the detected audio signals on the audio input to determine if the sound detected matches a voice reference sample of the user of the user ...

A musical tune playback apparatus is basically constituted by a controller (CPU), a digital media drive (e.g., a CD drive), a hard disk drive, and a sound system. Musical tune data recorded on a digital storage media (e.g., CD) are played back and are transferred to the hard disk drive together with relative information and/or image data. When a user inputs retrieval conditions, the controller retrieves musical tune data related to relative information (or image), which substantially matches ret...

A technique for generating an animated character based on visual and audio input from a live subject. Further described is a technique of extracting phonemes to select corresponding visemes to model a set of physical positions of the subject or emotional expression of the subject.

A method for recognizing an audio sample locates an audio file that most closely matches the audio sample from a database indexing a large set of original recordings. Each indexed audio file is represented in the database index by a set of landmark timepoints and associated fingerprints. Landmarks occur at reproducible locations within the file, while fingerprints represent features of the signal at or near the landmark timepoints. To perform recognition, landmarks and fingerprints are computed ...

A system and method for searching and selecting a specific read of a talent. A reel can be separated or marked to indicate individual reads. The reads are defined using read profiles. A producer and/or agent can perform searches and auditions on the search system on a read level by using the unique read profiles. The search for reads can be performed using sample voices or voices provided by a user. The auditions can be executed in real-time and can be integrated with telephony technology. Agent...

A printed media, such as a card bears a visible light image, such as a picture or photograph, for viewing by a human. A machine readable array of infra-red dots is located over the visible light image. In a preferred embodiment the infra-red dots encode sound recording data associated with the visible light image. Solomon-Reed encoding and checkerboard modulation of the dots is employed to ensure reliable retrieval of the sound recording.