Abstract: A system and method for improving the accuracy of audio searching using multiple models to process an audio file or stream to obtain search tracks. The search tracks are processed to locate at least one search term and generate multiple search results. The number of search results is equivalent to the number of models used to process the audio stream. The search results are combined to generate a unified search result. The multiple models may represent different languages, dialects and accents.

Abstract: In a multi-lingual environment, a method and apparatus for determining a language spoken in a speech utterance. The method and apparatus test acoustic feature vectors extracted from the utterances against acoustic models associated with one or more of the languages. Speech to text is then performed for the language indicated by the acoustic testing, followed by textual verification of the resulting text. During verification, the resulting text is processed by language specific NLP and verified against textual models associated with the language. The system is self-learning, i.e., once a language is verified or rejected, the relevant feature vectors are used for enhancing one or more acoustic models associated with one or more languages, so that acoustic determination may improve.

Abstract: A method and apparatus for analyzing and segmenting a vocal interaction captured in a test audio source, the test audio source captured within an environment. The method and apparatus first use text and acoustic features extracted from the interaction with tagging information, for constructing a model. Then, at production time, text and acoustic features are extracted from the interactions, and by applying the model, tagging information is retrieved for the interaction, enabling analysis, flow visualization or further processing of the interaction.

Abstract: Methods and apparatus for the enhancement of speech to text engines, by providing indications to the correctness of the found words, based on additional sources besides the internal indication provided by the STT engine. The enhanced indications comprise sources of data such as acoustic features, CTI features, phonetic search and others. The apparatus and methods also enable the detection of important or significant keywords found in audio files, thus enabling more efficient usages, such as further processing or transfer of interactions to relevant agents, escalation of issues, or the like. The methods and apparatus employ a training phase in which word model and key phrase model are generated for determining an enhanced correctness indication for a word and an enhanced importance indication for a key phrase, based on the additional features.

Abstract: A method and apparatus for automatic quality evaluation of an activity related to an organization, such as an agent of an organization which interacts with a calling party, a product, a campaign or the like, based on any combination of one or more of the following: the interaction itself and particularly its vocal part; meta data related to the call, to the call parties or to the environment; information extracted from the call or general information. The method may be activated off-line or on-line, in which case all alert can be generated for one or more calls.

Abstract: A method and apparatus for indexing one or more audio signals using a speech to text engine and a phoneme detection engine, and generating a combined lattice comprising a text part and a phoneme part. A word to be searched is searched for in the text part, and if not found, or is found with low certainty is divided into phonemes and searched for in the phoneme parts of the lattice.

Abstract: A method and apparatus for determining whether a speaker uttering an utterance belongs to a predetermined set comprising known speakers, wherein a training utterance is available for each known speaker. The method and apparatus test whether features extracted from the tested utterance provide a score exceeding a threshold when matched against one or more of models constructed upon voice samples of each known speaker. The method and system further provide optional enhancements such as determining, using, and updating model normalization parameters, a fast scoring algorithm, summed calls handling, or quality evaluation for the tested utterance.

Abstract: A method and apparatus for laughter detection. Laughter is detected through the presence of a sequence of at least a predetermined number such as three consecutive bursts, each burst comprising a voiced portion and an unvoiced portion. After detecting bursts, n-tuples such as triplets are detected, and a likelihood of each burst N-tuple to represent laughter is provided by comparison to predetermined thresholds. Finally, a total score is assigned to the signal based on the grades associated with the triplets and parameters such as the distance between the N-tuples, the total score representing the probability that the audio signal comprises a laughter episode. The method and apparatus preferably comprise a training step and module for determining the thresholds according to manually marked audio signals.

Abstract: A method and apparatus for automated categorization of an interaction between a member of an organization and a second party. The method comprises defining one or more criteria and one or more categories, wherein each category relates to a combination of one or more criteria. The criteria involve data extracted from the interactions as well as external data. Each interaction is checked against the criteria, and is then assigned to one or more categories according to the met criteria. An optional evaluation of the categorization step, and improvement of the categorization if the evaluation results fall below a threshold are disclosed.

Abstract: A fraud detection method for generating a first fraud or fraud attempt probability, within an at least one captured or recorded interaction, is provided. The method comprises a scoring step for scoring an at least one voice belonging to an at least one tested speaker in the at least one captured or recorded interaction against an at least one voice print within an at least one entry in a voice print collection, the scoring step generating an at least one probability that the at least one voice in the captured or recorded interaction belongs to an at least one second speaker associated with the at least one voice print, said at least one probability represents the probability that the at least one captured or recorded interaction is fraudulent; and an auditing step for auditing the at least one probability and the at least one captured or recorded interaction.

Abstract: A method and apparatus for automatic quality evaluation of an activity related to an organization, such as an agent of an organization which interacts with a calling party, a product, a campaign or the like, based on any combination of one or more of the following: the interaction itself and particularly its vocal part; meta data related to the call, to the call parties or to the environment; information extracted from the call or general information. The method may be activated off-line or on-line, in which case all alert can be generated for one or more calls.

Abstract: An apparatus and method for detecting a fraud or fraud attempt in a captured interaction. The method comprising a selection step in which interactions suspected as capturing fraud attempts are selected for further analysis, and assigned a first fraud probability, and a fraud detection step in which the voice is scored against one or more voice prints, of the same alleged customer or of known fraudsters. The first fraud or fraud attempt probability is combined with the result of the scoring of the fraud detection step, to generate a total fraud or fraud attempt probability. If the total fraud or fraud attempt probability exceeds a threshold, a notification is issued. The selection, scoring and combination thereof are performed using user-defined rules and thresholds.

Abstract: An apparatus and method for detecting an emotional state of a speaker participating in an audio signal. The apparatus and method are based on the distance in voice features between a person being in an emotional state and the same person being in a neutral state. The apparatus and method comprise a training phase in which a training feature vector is determined, and an ongoing stage in which the training feature vector is used to determine emotional states in a working environment. Multiple types of emotions can be detected, and the method and apparatus are speaker-independent, i.e., no prior voice sample or information about the speaker is required.

Abstract: An apparatus and method for detecting a fraud or fraud attempt in a captured interaction. The method comprising a selection step in which interactions suspected as capturing fraud attempts are selected for further analysis, and assigned a first fraud probability, and a fraud detection step in which the voice is scored against one or more voice prints, of the same alleged customer or of known fraudsters. The first fraud or fraud attempt probability is combined with the result of the scoring of the fraud detection step, to generate a total fraud or fraud attempt probability. If the total fraud or fraud attempt probability exceeds a threshold, a notification is issued. The selection, scoring and combination thereof are performed using user-defined rules and thresholds.

Abstract: An apparatus and method for an improved audio analysis process is disclosed. The improvement concerns the accuracy level of the results and the rate of false alarms produced by the audio analysis process. The proposed apparatus and method provides a three-stage audio analysis route. The three-stage analysis process includes a pre-analysis stage, a main analysis stage and a post analysis stage.

Abstract: A method and apparatus for spotting a target speaker within a call interaction by generating speaker models based on one or more speaker's speech; and by searching for speaker models associated with one or more target speaker speech files.

Abstract: A system and method for improving the accuracy of audio searching using multiple models to process an audio file or stream to obtain search tracks. The search tracks are processed to locate at least one search term and generate multiple search results. The number of search results is equivalent to the number of models used to process the audio stream. The search results are combined to generate a unified search result. The multiple models may represent different languages, dialects and accents.