Abstract: An in-call virtual assistant system monitors a real-time call, e.g., a call that is in progress, between multiple speakers, identifies a trigger and executes a specified task in response to the trigger. The virtual assistant system can be invoked by an explicit trigger or an implicit trigger. For example, an explicit trigger can be a voice command from one of the speakers in the call, such as “Ok Chorus, summarize the call” for summarizing the call. An implicit trigger can be an event that occurred in the call, or outside of the call but that is relevant to a speaker. For example, an event such as a speaker dropping off the call suddenly can be an implicit trigger that invokes the virtual assistant system to perform an associated task, such as notifying the remaining speakers on the call that one of the speakers dropped.

Abstract: An action item identification system automatically determines action items by analyzing conversations of representatives with customers. The action item identification system retrieves recordings of various conversations, extracts features of each of the conversations, and analyzes the features to determine a set of features that is indicative of an action item associated with the corresponding conversation. The set of features is further analyzed to generate the action item in an action item manifest (a) as a summary of what is discussed in the conversations or (b) verbatim from the conversations.

Abstract: A speaker identification system (“system”) automatically assigns a speaker to voiced segments in a conversation, without requiring any previously recorded voice sample or any other action by the speaker. The system enables unsupervised learning of speakers' fingerprints and using such fingerprints for identifying a speaker in a recording of a conversation. The system identifies one or more speakers, e.g., representatives of an organization, who are in conversation with other speakers, e.g., customers of the organization. The system processes recordings of conversations between a representative and one or more customers to generate multiple voice segments having a human voice, identifies the voice segments that have the same or a similar feature, and determines the voice in the identified voice segments as the voice of the representative.

Abstract: A speaker identification system (“system”) automatically assigns a speaker to voiced segments in a call. The system identifies one or more speakers in a call using one or more speaker-identification parameters. The system processes the call to determine one or more speaker-identification parameters, such as a transcript of the call, a facial image of the speaker, a scene image, which is an image of a scene in which the speaker is located during the call, or textual data associated with the call such as names of the speaker or an organization that are retrieved from the scene images or video data of the call. The system analyzes one or more of the speaker-identification parameters and determines the identity of the speaker. The system then identifies the voice segments associated with the identified speaker and marks the voice segments with the identity of the speaker.

Abstract: A risk identification system automatically determines deals at risk by analyzing conversations of representatives with customers. The risk identification system retrieves recordings of various conversations, extracts features of each of the conversations, and analyzes the features to determine if any of the conversations includes features that are indicative of a deal discussed in that conversation being at risk. By performing such an analysis of conversations, the risk identification system can identify a number of deals that are at risk and generate a report of such deals and notify a consumer user of the risk identification system of such deals.

Abstract: A call-modeling system models calls in real-time, with the goal of helping users, e.g., a sales representative and/or their managers, improve and/or guide the outcome of the calls. The call-modeling system generates real-time probabilities for possible outcomes of the conversation, as well as highlight specific on-call patterns, which may be either conducive or detrimental to a desired conversation outcome. The generated probabilities and highlighted patterns may be used by the sales representatives and/or their managers to either increase the probability of a desired outcome and/or optimize for call duration with a specific outcome.

Abstract: A pattern recognition system (“system”) automatically determines conversation patterns that distinguish a first set of participants from a second set of participants. For example, a first set of participants can be top performing representatives and the second set of participants can be low performing representatives. The system analyzes a first set of recordings of the top performing representatives to extract a first set of features associated with the first set of recordings, and analyzes the first set of features to generate first pattern data that is indicative of a pattern of the conversation of the top performing representatives. Similarly, the system also generates second pattern data that is indicative of a pattern of the conversation of the low performing representatives. The system analyzes the first pattern data and the second pattern data to generate distinctive features that distinguish the first pattern from the second pattern.

Abstract: A call-modeling system models calls in real-time, with the goal of helping users, e.g., a sales representative and/or their managers, improve and/or guide the outcome of the calls. The call-modeling system generates real-time probabilities for possible outcomes of the conversation, as well as highlight specific on-call patterns, which may be either conducive or detrimental to a desired conversation outcome. The generated probabilities and highlighted patterns may be used by the sales representatives and/or their managers to either increase the probability of a desired outcome and/or optimize for call duration with a specific outcome.

Abstract: The disclosure is directed to automatically determining product features that are a favorite of customers by analyzing conversations of representatives with the customers. A product functionality identification system retrieves recordings of various conversations, extracts features of the conversations, and analyzes the features to determine a set of features that is indicative of favorite functionalities of a product for one or more customers. A favorite functionality is one of multiple product features that is determined to be a favorite of one or more customers. The set of features is further analyzed to generate a favorite functionality manifest, which includes information regarding the favorite functionalities (a) as a summary of what is discussed in the conversations or (b) verbatim from the conversations.

Abstract: The disclosure is directed to automatically determining customer pain points by analyzing conversations of representatives with customers. A feedback identification system retrieves recordings of various conversations, extracts features of the conversations, and analyzes the features to determine a set of features that is indicative of a customer pain point. A customer pain point is a problem the customer is facing with a product. The set of features is analyzed to generate a feedback manifest, which includes the customer pain point (a) as a summary of what is discussed in the conversations or (b) verbatim from the conversations.

Abstract: The disclosure is directed to automatically determining product feature requests by analyzing conversations of representatives with customers. A feedback identification system retrieves recordings of various conversations, extracts features of the conversations, and analyzes the features to determine a set of features that is indicative of a feature request. A feature request is a request for adding a specified functionality to a product. The set of features is analyzed to generate a feedback manifest, which includes the feature request (a) as a summary of what is discussed in the conversations or (b) verbatim from the conversations.

Abstract: The disclosure is directed to automatically determining action items by analyzing conversations of representatives with customers. An action item identification system retrieves recordings of various conversations, extracts features of each of the conversations, and analyzes the features to determine a set of features that is indicative of an action item associated with the corresponding conversation. The set of features is further analyzed to generate the action item in an action item manifest (a) as a summary of what is discussed in the conversations or (b) verbatim from the conversations.

Abstract: The disclosure is directed to automatically determining deals at risk by analyzing conversations of representatives with customers. A risk identification system retrieves recordings of various conversations, extracts features of each of the conversations, and analyzes the features to determine if any of the conversations includes features that are indicative of a deal discussed in that conversation being at risk. By performing such an analysis of conversations, the risk identification system can identify a number of deals that are at risk and generate a report of such deals and notify a consumer user of the risk identification system of such deals.

Abstract: The disclosure is directed to automatically determining conversation patterns that distinguish a first set of participants from a second set of participants. For example, a first set of participants can be top-performing representatives and the second set of participants can be low-performing representatives. A pattern recognition system analyzes a first set of recordings of the top-performing representatives to extract a first set of features associated with the first set of recordings, and analyzes the first set of features to generate first pattern data that is indicative of a pattern of the conversation of the top-performing representatives. Similarly, the pattern recognition system also generates second pattern data that is indicative of a pattern of the conversation of the low-performing representatives. The pattern recognition system analyzes the first pattern data and the second pattern data to generate distinctive features that distinguish the first pattern from the second pattern.

Abstract: The disclosure is directed to analyzing voice conversations between participants of conversations and coordinating calls between participants, e.g., in order to influence an outcome of the voice conversation. For example, sales calls can be coordinated between specific sales representatives (“representatives”) and customers by routing a sales call from a customer to a specific sales representative, based on their voices and the content of the conversation, with the goal of positively influencing the outcome of the sales call. A mapping between sales representatives and customers that is set to maximize the probability for certain outcomes is generated. This mapping (or pairing) may be fed into either an automatic or manual coordination system that connects or bridges sales representatives with customers. The mapping may be generated either based on historic data or early-call conversation analysis, in both inbound and outbound calls.

Abstract: The disclosure is directed to automatically generating a playlist of conversations having a specified moment. A moment can be occurrence of a specific event or a specific characteristic in a conversation, or any event that is of specific interest for an application for which the playlist is being generated. For example, a moment can include laughter, fast-talking, objections, response to questions, a discussion on a particular topic such as budget, behavior of a speaker, intent to buy, etc., in a conversation. A moment identification system analyzes each of the conversations to determine if one or more features of a conversation correspond to a specified moment, and includes those of the conversations in the playlist having one or more features that correspond to the specified moment. The playlist may include a portion of a conversation that has the specified moment rather than the entire conversation.

Abstract: The disclosure is directed to analyzing voice conversations between participants of conversations and coordinating calls between participants, e.g., in order to influence an outcome of the voice conversation. For example, sales calls can be coordinated between specific sales representatives (“representatives”) and customers by routing a sales call from a customer to a specific sales representative, based on their voices and the content of the conversation, with the goal of positively influencing the outcome of the sales call. A mapping between sales representatives and customers that is set to maximize the probability for certain outcomes is generated. This mapping (or pairing) may be fed into either an automatic or manual coordination system that connects or bridges sales representatives with customers. The mapping may be generated either based on historic data or early-call conversation analysis, in both inbound and outbound calls.

Abstract: The disclosure is directed to analyzing voice conversations between participants of conversations and coordinating calls between participants, e.g., in order to influence an outcome of the voice conversation. For example, sales calls can be coordinated between specific sales representatives (“representatives”) and customers by routing a sales call from a customer to a specific sales representative, based on their voices and the content of the conversation, with the goal of positively influencing the outcome of the sales call. A mapping between sales representatives and customers that is set to maximize the probability for certain outcomes is generated. This mapping (or pairing) may be fed into either an automatic or manual coordination system that connects or bridges sales representatives with customers. The mapping may be generated either based on historic data or early-call conversation analysis, in both inbound and outbound calls.

Abstract: The disclosure is directed to modeling calls in real time, with the goal of helping users, e.g., a sales representative and/or their managers, improve and/or guide the outcome of the calls. The embodiments generate real-time probabilities for possible outcomes of the conversation, as well as highlight specific on-call patterns, which may be either conducive or detrimental to a desired conversation outcome. The generated probabilities and highlighted patterns may be used by the sales representatives and/or their managers to either increase the probability of a desired outcome and/or optimize for call duration with a specific outcome.

Abstract: The disclosure is directed to analyzing voice conversations between participants of conversations and coordinating calls between participants, e.g., in order to influence an outcome of the voice conversation. For example, sales calls can be coordinated between specific sales representatives (“representatives”) and customers by routing a sales call from a customer to a specific sales representative, based on their voices and the content of the conversation, with the goal of positively influencing the outcome of the sales call. A mapping between sales representatives and customers that is set to maximize the probability for certain outcomes is generated. This mapping (or pairing) may be fed into either an automatic or manual coordination system that connects or bridges sales representatives with customers. The mapping may be generated either based on historic data or early-call conversation analysis, in both inbound and outbound calls.