Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for analyzing an audio to capture semantic and non-semantic characteristics of the audio and corresponding relationships between the semantic and non-semantic characteristics. In particular embodiments, the audio is segmented into a set of utterance segments containing a party speaking on the audio and a set of noise segments containing the party not speaking on the audio. The semantic and non-semantic characteristics are then captured for each of the utterance segments. Specifically, speech analytics is performed on each segment to identify the words spoken by the party in the segment as semantic characteristics. Further, laughter, emotion, and sentence boundary detection is performed on each segment to identify occurrences of such in the segment as non-semantic characteristics.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for analyzing an audio to capture semantic and non-semantic characteristics of the audio and corresponding relationships between the semantic and non-semantic characteristics. In particular embodiments, the audio is segmented into a set of utterance segments containing a party speaking on the audio and a set of noise segments containing the party not speaking on the audio. The semantic and non-semantic characteristics are then captured for each of the utterance segments. Specifically, speech analytics is performed on each segment to identify the words spoken by the party in the segment as semantic characteristics. Further, laughter, emotion, and sentence boundary detection is performed on each segment to identify occurrences of such in the segment as non-semantic characteristics.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for analyzing an audio to capture semantic and non-semantic characteristics of the audio and corresponding relationships between the semantic and non-semantic characteristics. In particular embodiments, the audio is segmented into a set of utterance segments containing a party speaking on the audio and a set of noise segments containing the party not speaking on the audio. The semantic and non-semantic characteristics are then captured for each of the utterance segments. Specifically, speech analytics is performed on each segment to identify the words spoken by the party in the segment as semantic characteristics. Further, laughter, emotion, and sentence boundary detection is performed on each segment to identify occurrences of such in the segment as non-semantic characteristics.

Abstract: An approach for optimizing a confidence score threshold that is used to recognize a target word(s) in an audio source. A variety of potential instances of the target word can be detected and classified using an initial confidence score threshold value. Each potential instance of the target word is audibly reviewed and validated by a user. After a determination of the correctness of each potential instance's classification, a different confidence score threshold value can be used to produce an updated set of classification results without requiring the user to revalidate the results. By using a variety of confidence score threshold values to produce various sets of classification results, an optimized confidence threshold setting can be determined for the identified target word based on minimizing errors in the various results. This value can then be applied for future analysis of the target word in an audio source.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for pacing outbound calls placed by a predictive dialer in a contact center. Specifically, an ensemble made up of a global predictive model and a local predictive model is applied to each dialing record found in a plurality of dialing records to provide a probability of an outbound call placed to the dialing record resulting in a live connect. Accordingly, a call pacing hit ratio can then be calculated based on the probability for each of the dialing records and this call pacing hit ratio can be used by a predictive dialer in various embodiments to more accurately pace the placing of outbound calls then by using conventionally derived call pacing hit ratios.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for pacing outbound calls placed by a predictive dialer in a contact center. Specifically, an ensemble made up of a global predictive model and a local predictive model is applied to each dialing record found in a plurality of dialing records to provide a probability of an outbound call placed to the dialing record resulting in a live connect. Accordingly, a call pacing hit ratio can then be calculated based on the probability for each of the dialing records and this call pacing hit ratio can be used by a predictive dialer in various embodiments to more accurately pace the placing of outbound calls then by using conventionally derived call pacing hit ratios.

Abstract: An automatic list scheduling (“ALS”) system monitors usage of calling lists by an administrator where the administrator terminates usage of a calling list based on various measured parameters. The ALS system is configure to learn the conditions associated with the measured parameters and, in one embodiment, recommends to the administrator when to terminate use of a current calling list in favor of another list. A learning mode gathers various samples of the measured parameters associated with calling lists, and analyzes the sample to determine a threshold value. Upon monitoring the measured values for subsequent usage of calling lists, the current measured parameters are compared to the threshold value to determine whether to generate a recommendation to the administrator. In one embodiment, the time zone of the called party and the applicable calling window is used to determine whether the current list can continued to be used.

Abstract: An automatic list scheduling (“ALS”) system monitors usage of calling lists by an administrator where the administrator terminates usage of a calling list based on various measured parameters. The ALS system is configure to learn the conditions associated with the measured parameters and, in one embodiment, recommends to the administrator when to terminate use of a current calling list in favor of another list. A learning mode gathers various samples of the measured parameters associated with calling lists, and analyzes the sample to determine a threshold value. Upon monitoring the measured values for subsequent usage of calling lists, the current measured parameters are compared to the threshold value to determine whether to generate a recommendation to the administrator. In one embodiment, the time zone of the called party and the applicable calling window is used to determine whether the current list can continued to be used.

Abstract: Various methods, systems, and computer-program products are provided for indicating a message characteristic indicator (“MCI”) in conjunction with a stored voice message. In various applications where voice messages may be received, a speech analytics system processes the voice message to ascertain a non-semantic speech-related characterization of the message. An indication of a corresponding MCI, such as an emoticon, is associated with the stored message, which can be used to display the corresponding MCI on a user interface. In one embodiment, the stored voice message is a voice mail message received in conjunction with a call to a wireless user. A voice mail storage system utilizes a speech analytics system to process the voice data and ascertain the non-semantic speech-related characterization of the message and a message is sent to the subscriber's mobile phone indicating the appropriate MCI to display in conjunction with the meta-data of the voice mail message.

Abstract: A reserve agent management system allows users, such as contact center agents or administrators, to access and edit reserve schedules for agents. In various embodiments, a reserve schedule indicates times, called reserve times, during a particular agent's off-hours when the agent is willing to receive a recall invitation and potentially return to work. Thus, when a determination is made that additional agent resources are needed, agents having compatible reserve times are notified and invited to be recalled. Agents agreeing to be recalled are then scheduled to work at certain recall times to address the need for additional agent resources. In other embodiments, agents' break times may be shifted to potentially accommodate unexpected changes in required agent resources. Thus, in various embodiments, the reserve agent management system provides administrators and agents with flexibility in adapting agents' schedules to accommodate unplanned needs for agent resources.