Abstract: An audio fingerprint is generated by transforming an audio sample of a recording to a time-frequency domain and storing each time-frequency pair in a matrix array, detecting a plurality of local maxima for a predetermined number of time slices, selecting a predetermined number of largest-magnitude maxima from the plurality of local maxima detected by said detecting, and generating one or more hash values corresponding to the predetermined number of largest-magnitude maxima.

Abstract: An input feature vector is computed from an input text record, the input feature vector comprising one or more features, each feature including a subsequence of characters and a frequency of occurrence of the associated subsequence. A input fingerprint is generated out of the input feature vector by choosing one or more features with non-zero frequencies and alphabetizing the features chosen. One or more input indices are generated by alphabetizing features in the input fingerprint and concatenating features occurring in subsequent locations of the input fingerprint. The input text record is matched against a target text record if (1) one or more of the input indices match a target index corresponding to the target text record and (2) the corresponding input fingerprint matches a target fingerprint corresponding to the target text record. The target text record is outputted as a search result if it matches the input text record.

Abstract: An input feature vector is computed from an input text record, the input feature vector comprising one or more features, each feature including a subsequence of characters and a frequency of occurrence of the associated subsequence. A input fingerprint is generated out of the input feature vector by choosing one or more features with non-zero frequencies and alphabetizing the features chosen. One or more input indices are generated by alphabetizing features in the input fingerprint and concatenating features occurring in subsequent locations of the input fingerprint. The input text record is matched against a target text record if (1) one or more of the input indices match a target index corresponding to the target text record and (2) the corresponding input fingerprint matches a target fingerprint corresponding to the target text record. The target text record is outputted as a search result if it matches the input text record.

Abstract: A system for discovering content and metadata includes a processor communicatively coupled to a communication network and a database. The processor determines whether an end portion of a portion of content has been received based on the portion of content and/or metadata. The processor generates a content fingerprint based on the portion of content if the end portion has been received. The content fingerprint and/or the metadata are stored in the database.

Abstract: A system includes a processor that retrieves, from a first database, a portion of content associated with time-localized metadata. The time-localized metadata and a tag mode identifier are retrieved from a second database. A tag mode associated with the portion of content is determined based on the time-localized metadata and/or the tag mode identifier. The portion of content and/or the time-localized metadata are transmitted to a user device based on the tag mode. In some embodiments, a reconstruction mode associated with the portion of content is determined based on the time-localized metadata and/or a reconstruction mode identifier. The portion of content, the time-localized metadata, attribute information, and/or mapping information are transmitted to the user device based on the reconstruction mode.

Abstract: A system includes a processor that receives, via a communication channel, a portion of content associated with time-localized metadata. The time-localized metadata and a tag mode identifier are retrieved from a database. A tag mode associated with the portion of content is determined based on the time-localized metadata and/or the tag mode identifier. The processor implements a feature based on the time-localized metadata and the tag mode.

Abstract: A method and a system are provided for recommending a media item (e.g., movie and/or television program). In one example, the system receives a seed media item (e.g., seed movie and/or seed television program). A seed media item is an audio-visual recording that is identified as being of interest to a user. The system recognizes one or more recognized audio tracks (e.g., audio tracks and/or songs) from the seed media item. A recognized audio track is an audio recording that is contained in the seed media item. The system retrieves audio track metadata associated with at least one of the recognized audio tracks from the seed media item. Audio track metadata are data that describes an audio recording. The system recommends one or more recommended media items based on the audio track metadata. A recommended media item is an audio-visual recording (e.g., movie and/or television program).

Abstract: A method and a system are provided for recommending a media item (e.g., movie and/or television program). In one example, the system receives a seed media item (e.g., seed movie and/or seed television program). A seed media item is an audio-visual recording that is identified as being of interest to a user. The system recognizes one or more recognized audio tracks (e.g., audio tracks and/or songs) from the seed media item. A recognized audio track is an audio recording that is contained in the seed media item. The system retrieves audio track metadata associated with at least one of the recognized audio tracks from the seed media item. Audio track metadata are data that describes an audio recording. The system recommends one or more recommended media items based on the audio track metadata. A recommended media item is an audio-visual recording (e.g., movie and/or television program).

Abstract: An audio fingerprint is generated by transforming an audio sample of a recording to a time-frequency domain and storing each time-frequency pair in a matrix array, detecting a plurality of local maxima for a predetermined number of time slices, selecting a predetermined number of largest-magnitude maxima from the plurality of local maxima detected by said detecting, and generating one or more hash values corresponding to the predetermined number of largest-magnitude maxima.

Abstract: A multi-stage lookup is performed by receiving a query fingerprint of an unknown recording, generating a hash value corresponding to the query fingerprint; generating a list of candidate matches of known recordings by comparing the hash value of the query fingerprint to a hash table containing multiple hash values corresponding to audio fingerprints of the known recordings, comparing maxima of the query fingerprint to the maxima of full-recording fingerprints of the known recordings contained in a full-recording fingerprint table to obtain an identifier corresponding to the unknown recording, and returning metadata based on the identifier.