Abstract: A method includes processing a number of media assets stored in one or more media asset repositories to determine a number of signatures for media in time intervals of the media assets of the number of media assets, processing the number signatures to identify duplicate instances of the signatures in the number of signatures, processing the identified duplicate instances to identify relationships between the identified duplicate instances, and storing the number of signatures and the relationships between the identified duplicate instances of the signatures in a signature data store.

Abstract: A transcription system automates the control of the playback of the audio to accommodate the user's ability to transcribe the words spoken. In some examples, a delay between playback and typed input is estimated by processing the typed words using a wordspotting approach. The estimated delay is used as in input to an automated speed control, for example, to maintain a target or maximum delay between playback and typed input.

Abstract: A method for determining evaluation information using audio data includes receiving a specification of an evaluation form, the evaluation form including a number of questions, each question having a number of possible answers. A user is received indicating that a first answer of the number of possible answers for a first question of the number of questions should be determined automatically from the audio data, the audio data including speech of a subject. A user input is received associating a first constraint of a plurality of constraints with the first answer. The audio data is processed to determine whether the audio data putatively satisfies the first constraint. The first answer is assigned as an answer to the first question if the audio data putatively satisfies the first constraint. The first answer is stored as the answer to the first question in the evaluation form.

Abstract: A method for analysis of a set of media recordings includes, in a first processing stage, selecting a subset of the set of media recordings by performing a first processing of each media recording of the set of media recordings and in a second processing stage, performing a second processing of the subset of the set of media recordings, the second processing including extraction of information from the media recordings of the subset of the set of media recordings. The first processing of each media recording of the set of media recordings includes determining a characterization of the media recording, the characterization including at least a quantity characterizing a predicted performance of the second processing of the media recording.

Abstract: In a general aspect, an approach to query specification includes processing a query by identifying one or more terms and validating the terms using a first corpus of media elements. The result of the validation is used to form a modified query. In some examples, identifying the one or more terms is based on a second corpus of media elements, which may include a different type of media than the first corpus. In some examples, the validating of the terms includes accepting input from a user according to parts of the elements of the first corpus presented to the user.

Abstract: A method for preparing supplementary media content for coordinated transmission with multimedia content includes accepting the multimedia content including an audio portion, accepting the supplementary media content associated with the multimedia content, and validating the supplementary media content according to the audio portion of the multimedia content.

Abstract: In an aspect, in general, method for aligning an audio recording and a transcript includes receiving a transcript including a plurality of terms, each term of the plurality of terms associated with a time location within a different version of the audio recording, forming a plurality of search terms from the terms of the transcript, determining possible time locations of the search terms in the audio recording, determining a correspondence between time locations within the different version of the audio recording associated with the search terms and the possible time locations of the search terms in the audio recording, and aligning the audio recording and the transcript including updating the time location associated with terms of the transcript based on the determined correspondence.

Abstract: In one aspect, a method for processing media includes accepting a query. One or more language patterns are identified that are similar to the query. A putative instance of the query is located in the media. The putative instance is associated with a corresponding location in the media. The media in a vicinity of the putative instance is compared to the identified language patterns and data characterizing the putative instance of the query is provided according to the comparing of the media to the language patterns, for example, as a score for the putative instance that is determined according to the comparing of the media to the language patterns.

Abstract: Systems, methods, and apparatus, including computer program products for accepting a predetermined vocabulary-dependent characterization of a set of audio signals, the predetermined characterization including an identification of putative occurrences of each of a plurality of vocabulary items in the set of audio signals, the plurality of vocabulary items included in the vocabulary; accepting a new vocabulary item not included in the vocabulary; accepting putative occurrences of the new vocabulary item in the set of audio signals; and generating, by an analysis engine of a speech processing system, an augmented characterization of the set of audio signals based on the identified putative occurrences of the new vocabulary item.

Abstract: A method for speaker adaptation includes receiving a plurality of media files, each associated with a call center agent of a plurality of call center agents and receiving a plurality of terms. Speech processing is performed on at least some of the media files to identify putative instances of at least some of the plurality of terms. Each putative instance is associated with a hit quality that characterizes a quality of recognition of the corresponding term. One or more call center agents for performing speaker adaptation are determined, including identifying call center agents that are associated with at least one media file that includes one or more putative instances with a hit quality below a predetermined threshold. Speaker adaptation is performed for each identified call center agent based on the media files associated with the identified call center agent and the identified instances of the plurality of terms.

Abstract: In an aspect, in general, a computer implemented method includes receiving a query phrase, receiving a first data representing a first audio signal including an interaction among a number of speakers and at least one segment of one or more known audio items, receiving a second data comprising temporal locations of the at least one segment of one or more known audio items in the first audio signal, and searching the first data to identify putative instances of the query phrase that are temporally excluded from the temporal locations of the at least one segment of one or more known audio items.

Abstract: In an aspect, in general, a system includes a first input for receiving a first data representing an interaction among a plurality of parties, the first data identifying a plurality of parts of the interaction and identifying a plurality of segments associated with each part of the plurality of parts, a second input for receiving a second data associating each of one or more labels with one or more corresponding query phrases, a searching module for searching the first data to identify putative instances of the query phrases, and a classifier for labeling the parts of the interaction associated with the identified putative instances of the query phrases with the labels corresponding to the identified query phrases.

Abstract: An audio processing system makes use of a number of levels of compression or data reduction, thereby providing reduced storage requirements while maintaining a high accuracy of keyword detection in the original audio input.

Abstract: A method for determining a similarity between a first audio source and a second audio source includes: for the first audio source, determining a first frequency of occurrence for each of a plurality of phoneme sequences and determining a first weighted frequency for each of the plurality of phoneme sequences based on the first frequency of occurrence for the phoneme sequence; for the second audio source, determining a second frequency of occurrence for each of a plurality of phoneme sequences and determining a second weighted frequency for each of the plurality of phoneme sequences based on the second frequency of occurrence for the phoneme sequence; comparing the first weighted frequency for each phoneme sequence with the second weighted frequency for the corresponding phoneme sequence; and generating a similarity score representative of a similarity between the first audio source and the second audio source based on the results of the comparing.

Abstract: A method for speaker adaptation includes receiving a plurality of media files, each associated with a call center agent of a plurality of call center agents and receiving a plurality of terms. Speech processing is performed on at least some of the media files to identify putative instances of at least some of the plurality of terms. Each putative instance is associated with a hit quality that characterizes a quality of recognition of the corresponding term. One or more call center agents for performing speaker adaptation are determined, including identifying call center agents that are associated with at least one media file that includes one or more putative instances with a hit quality below a predetermined threshold. Speaker adaptation is performed for each identified call center agent based on the media files associated with the identified call center agent and the identified instances of the plurality of terms.

Abstract: A method includes accepting, via an input interface, a caller identifier parameter and a target value of at least one call series parameter; identifying, using a data processor, a plurality of calls each associated with the caller identifier parameter from amongst a set of calls stored in a call center database; analyzing, using the data processor, the identified plurality of calls to determine a value of the at least one call series parameter for the identified plurality of calls; comparing, using the data processor, the determined value of the at least one call series parameter with the target value of the at least one call series parameter; and defining, using the data processor, the identified plurality of calls as a call series based at least in part on results of the comparing.

Abstract: In a general aspect, an approach to query specification includes processing a query by identifying one or more terms and validating the terms using a first corpus of media elements. The result of the validation is used to form a modified query. In some examples, identifying the one or more terms is based on a second corpus of media elements, which may include a different type of media than the first corpus. In some examples, the validating of the terms includes accepting input from a user according to parts of the elements of the first corpus presented to the user.

Abstract: An information retrieval system for search a corpus is configured to, for each of a plurality of searches of at least a subset of the corpus, generate a confidence score for each of a plurality of putative occurrences of a search query in the at least a subset of the corpus. The system is further configured to adjust a threshold to maintain a consistent user experience across the plurality of searches according to a consistency criterion. The system is further configured to display putative occurrences of the search query having a confidence score greater than the threshold.

Abstract: Some general aspects of the invention relate to systems and methods for improving contact center agent performance, for instance, by integrating real-time call monitoring with speech analytics to present agents with information useful to the handling of the current calls. In some implementations, phonetically based speech analysis techniques are applied to process live audio streams to identify key words and/or phrases of relevance, based on which knowledge articles can be selectively presented to agents to drive more efficient business processes.

Abstract: In an aspect, in general, method for aligning an audio recording and a transcript includes receiving a transcript including a plurality of terms, each term of the plurality of terms associated with a time location within a different version of the audio recording, forming a plurality of search terms from the terms of the transcript, determining possible time locations of the search terms in the audio recording, determining a correspondence between time locations within the different version of the audio recording associated with the search terms and the possible time locations of the search terms in the audio recording, and aligning the audio recording and the transcript including updating the time location associated with terms of the transcript based on the determined correspondence.