Avaya Inc.

Aurix Limited

Qinetiq Limited

Keith M Ponting

Valentine C Matula

Wendy J Holmes

David Skiba

Mehmet Balasaygun

John F Buford

John Jacob

David Zeitlyn

Rein Sikveland

Shmuel Shaffer

Robert W Series

Mohammed Jahangir

James Michael Kirby

Martin G Abbott

Michael J Tomlinson

Darren Lee Standing

David Mark Timothy Edwards

Timothy Richard Edwards

Malcolm Fintan Wilkins

Neil Campbell

Embodiments disclosed herein provide systems, methods, and computer-readable media for detecting disturbances in a media stream from a participant on a communication. In a particular embodiment, a method provides receiving biometric information indicating a motion of the participant and determining that the motion indicates a visual disturbance in a video component of the first media stream. The method further provides identifying the visual disturbance in the video component of the first media stream and removing the visual disturbance from the video component of the first media stream.

Disturbance detection in video communications

Embodiments disclosed herein provide systems, methods, and computer readable media for detecting disturbances in a media stream from a participant on a communication. In a particular embodiment, a method provides identifying disturbance criteria defining a plurality of audible disturbances, a plurality of visual disturbances, and a plurality of communication disturbances. The method further provides identifying one or more audible disturbances from an audio component of the media stream based on predefined disturbance criteria and identifying one or more visual disturbances from a video component of the media stream based on the disturbance criteria. Additionally, the method provides correlating the audible disturbances with the visual disturbances to determine one or more combined disturbances for the participant based on the disturbance criteria, wherein each of the combined disturbances comprises at least one of the audible disturbances and at least one of the visual disturbances.

Embodiments disclosed herein provide systems, methods, and computer readable media for analyzing a conversation between a plurality of participants. In a particular embodiment, a method provides determining a first speaker from the plurality of participants and determining a second speaker from the plurality of participants. The method further provides determining a first plurality of turns comprising portions of the conversation when the first speaker is speaking and determining a second plurality of turns comprising portions of the conversation when the second speaker is speaking The method also provides determining per-turn statistics for turns of the first and second pluralities of turns and identifying phases of the conversation based on the per-turn statistics.

Conversation structure analysis

Methods and systems for identifying specified phrases within audio streams are provided. More particularly, a phrase is specified. An audio stream is them monitored for the phrase. In response to determining that the audio stream contains the phrase, verification from a user that the phrase was in fact included in the audio stream is requested. If such verification is received, the portion of the audio stream including the phrase is recorded. The recorded phrase can then be applied to identify future instances of the phrase in monitored audio streams.

Phrase spotting systems and methods

Embodiments disclosed herein provide systems, methods, and computer readable media for analyzing a conversation between a plurality of participants. In a particular embodiment, a method provides determining a first speaker from the plurality of participants and determining a second speaker from the plurality of participants. The method further provides determining a first plurality of turns comprising portions of the conversation when the first speaker is speaking and determining a second plurality of turns comprising portions of the conversation when the second speaker is speaking. The method further provides determining a characterization for quality of the conversation based on gaps between turns of the first plurality of turns and turns of the second plurality of turns.

Conversation quality analysis

An event associated with a communication session between a first party and a second party is detected. The event is related to the communication session. For example, the event may be a phrase spoken in the communication session or a presentation of a call progression screen to a contact center agent. At this point, the communication session is analyzed for a period of non-communication that meets a defined threshold during a monitoring period associated with the event. If a period of non-communication is detected that is longer than the threshold during the monitoring period, the period of non-communication is flagged. The flagged period of non-communication can then be used to evaluate how a contact center agent is performing.

Silence density models

To detect events in an audio stream, frames of an audio signal (e.g., frames generated by a codec for a voice call or music stream) are received. Based on information in the frames, an index is used to look up an entry in a table associated with the codec. Each entry in the table indicates a likelihood that a frame matches a sound model element. The likelihood is used in the search for a sound bite, word, and/or phrase in the audio signal. The process of dynamic programming is used to find the combined likelihood for a match of the word, phrase, and/or sound bite to a region of the audio stream. Upon detection of the word, phrase, and/or sound bite in the audio stream, an event is generated, such as, notifying a person or logging the event in a database.

Audio search using codec frames

System and method to search audio data, including: receiving audio data representing speech; receiving a search query related to the audio data; compiling, by use of a processor, the search query into a hierarchy of scored speech recognition sub-searches; searching, by use of a processor, the audio data for speech identified by one or more of the sub-searches to produce hits; and combining, by use of a processor, the hits by use of at least one combination function to provide a composite search score of the audio data. The combination function may include an at-least-M-of-N function that produces a high score when at least M of N function inputs exceed a predetermined threshold value. The composite search score employ a soft time window such as a spline function.

'At least' operator for combining audio search hits

Agents of a contact center often encounter conversational delays when speaking with a customer. These delays may be introduced by transmission delays, which include the distance between the agent and the customer, and processing delays, such as those introduced by systems and processes within a contact center. By providing an agent with information based on the amount of the delay, the agent can be prompted to overtalk the customer by a target amount. As a result, the customer may experience a more natural conversation with the agent. Furthermore, if a customer prefers more or less of a delay, such as based on their cultural norms, the delay may be modified to account for those cultural norms and better accommodate the conversational preferences of a diverse customer base.

Speech analytics: conversation timing and adjustment

In order to detect a specific codec sequence being used, a signal that is based on a codec sequence is analyzed. The signal is analyzed to determine if there is a pattern in the signal. A pattern of a codec sequence can be a unique pattern of frames, frequencies and/or frequency ranges that are generated based on a specific codec sequence. The pattern is compared to one or more previously stored patterns of codec sequences to see if there is a match. If there is a match, an event is generated. For example, if a known codec sequence that has a poor signal quality is determined to be in use for a voice call, the parties may be notified that the call is likely to be a low quality voice call.

Codec sequence detection

Apparatus for analyzing non-deterministic results of a search query of data, comprising a processor and a user interface, the processor being operably in communication with a plurality of data sources and adapted to communicate with the user interface which enables the user to query the content of the data sources, wherein the processor is adapted to determine the probable relevance of at least the part of a searched data source for a user query and the user interface is adapted to present to the user the search results in a form comprising two or more portlets, wherein the portlets comprises two or more of: a portlet presenting the search results (such as search strings) for a data source(s); a portlet presenting the data source (such as by source name) of a data source(s); a portlet presenting a data source filter tree for selecting currently active source(s); a portlet presenting the hit(s) of a search query for a data source; a portlet presenting the hit location within a data source; and at least one of the portlets presents the user with the probability of the relevance of the data source to the search query.

User interface for use in non-deterministic searching

This invention relates to a method of searching spoken audio data for one or more search terms comprising performing a phonetic search of the audio data to identify likely matches to a search term and producing textual data corresponding to a portion of the spoken audio data including a likely match. An embodiment of the method comprises the steps of taking phonetic index data corresponding to the spoken audio data, searching the phonetic index data for likely matches to the search term, wherein when a likely match is detected a portion of the spoken audio data or phonetic index data is selected which includes the likely match and said selected portion of the spoken audio data or phonetic index data is processed using a large vocabulary speech recognizer. The large vocabulary speech recognizer may derive textual data which can be used for further processing or may be used to present a transcript to a user. The present invention therefore combines the benefit of phonetic searching of audio data with the advantages of large vocabulary speech recognition.

Methods and apparatus relating to searching of spoken audio data

A method of recognizing a radar target comprises producing a sequence of Doppler spectra of radar returns form a scene and producing therefrom a sequence of Doppler feature vectors for a target in the scene. Hidden Markov modelling (HMM) is then used to identify the sequence of Doppler feature vectors as indicating a member of a particular class of targets. HMM is used to identify the sequence of Doppler feature vectors by assigning to each feature vector an occurrence probability by selecting a probability distribution or state from a set thereof associated with a class of targets, multiplying the occurrence probabilities together to obtain an overall probability, repeating for other probability distributions in the set to determine a combination of probability distributions giving highest overall probability for that class of target, then repeating for at least one other class of targets and selecting the target class as being that which yields the highest overall occurrence probability.

Growing community of inventors

Worcs, United Kingdom

Keith M Ponting