Abstract: A computer-implemented method and apparatus for extracting key information from conversational voice data, where the method comprises receiving a first speaker text corresponding to a speech of a first speaker in a conversation with a second speaker, the conversation comprising multiple turns of speech between the first speaker and the second speaker, the first speaker text comprising multiple question lines, each question line corresponding to the speech of the first speaker at a corresponding turn, arranged chronologically. Feature words are identified, and a frequency of occurrence therefor in each question line is determined. Question lines without any of the feature words are removed, to yield candidate question lines, for each of which a mathematical representation is generated. A similarity score for each candidate question line with respect to each subsequent candidate question line is computed, and the line with the highest score is identified as a key question.

Abstract: A method and an apparatus for predicting satisfaction of a customer pursuant to a call between the customer and an agent, in which the method comprises receiving a transcribed text of the call, dividing the transcribed text into a plurality of phases of a conversation, extracting at least one call feature for each of the plurality of phases, receiving call metadata, extracting metadata features from the call metadata, combining the call features and the metadata features, and generating an output, using a trained machine learning (ML) model, based on the combined features, indicating whether the customer is satisfied or not. The ML model is trained to generate an output indicating whether the customer is satisfied or not, based on an input of the combined features.

Abstract: A system for categorizing a call between an agent and a caller comprises at least one processor and a memory communicably coupled to the at least one processor. The memory comprises computer executable instructions, which, when executed by the at least one processor implement a method as follows. A call document comprising text of the call between the agent and the caller is received by the system. The system categorizes the call into at least one class using regressive probability analysis of the call document. The system splits the call document to at least two portions, the at least two portions comprising a call header and a call body, and thereafter, using rule-based entity extraction, the system extracts a mandatory entity from the call header and an optional entity from the call body.

Abstract: A method and an apparatus for coaching call center agents is provided. The method includes analyzing a conversation of the agent with a first customer, determining a performance of the agent on at least one behavioral skill based on the analysis, generating automatically, a custom training package (CTP) based on the determined first performance, and sending the CTP for presentation on the agent device.

Abstract: A method and an apparatus for automatic speaker diarization is provided. The method includes removing, at a call analytics server (CAS), non-speech portions from a call audio to produce a pre-processed audio, the call audio comprising speech from at least two speakers. Next, the pre-processed audio is divided, at the CAS, to multiple audio segments, each segment corresponding to speech from a single speaker of the at least two speakers. Next, the plurality of segments are clustered, at the CAS, into at least two groups corresponding the at least two speakers.

Abstract: A dynamic speech processing system and method is provided. The system includes a receiver configured to receive a plurality of audio files. The audio files include sample training audio files and run-time audio files. The system further includes a speech processor coupled to the receiver and configured to compute a variable value for a specific audio file. The speech processor is configured to dynamically select a set of relevant speech recognition engines for a specific run-time audio file based on the variable value.

Abstract: A dynamic speech processing system and method is provided. The system includes a receiver configured to receive a plurality of audio files. The audio files include sample training audio files and run-time audio files. The system further includes a speech processor coupled to the receiver and configured to compute a variable value for a specific audio file. The speech processor is configured to dynamically select a set of relevant speech recognition engines for a specific run-time audio file based on the variable value.

Abstract: A speech analytics system configured to detect an event is provided. The speech analytics system includes a graphical user interface configured to enable one or more users to upload one or more audio files. The speech analytics system also includes a rules configurator engine configured to receive and store a plurality of event rules. The plurality of event rules are provided by the one or more users via the graphical user interface. Further, the plurality of event rules stored in the rules configurator engine is reconfigurable by the one or more users. In addition, the speech analytics system includes an event detection module coupled to the rules configurator engine and configured to detect the event by processing the audio file. Lastly, the speech analytics system includes an event reporting module configured to notify the event to the one or more users.

Abstract: A voice biometrics system adapted to authenticate a user based on speech diagnostics is provided. The system includes a pre-processing module to receive and pre-process an input voice sample. The pre-processing module includes a clipping module to clip the input voice sample based on a clipping threshold and a voice activity detection module to apply a detection model on the input voice sample to determine an audible region and a non-audible region in the input voice sample. The pre-processing module includes a noise reduction module to apply a noise reduction model to remove noise components from the input voice sample. The voice biometrics system includes a feature extraction module to extract features from the pre-processed input voice sample. The voice biometrics system also includes an authentication module to authenticate the user by comparing a plurality of features extracted from the pre-processed input voice sample to a plurality of enrollment features.