Abstract: Methods and apparatus are disclosed for priority based audio mixing. At least one audio characteristic of one or more audio streams is modified to convey a relative priority of the audio streams, prior to mixing the audio streams. The adjusted audio characteristic may be, for example, a volume, pitch or speed of one or more audio streams. The relative priority information may be based, for example, on an analysis of the content of one or more of the audio streams. In further variations, the priority is based on one or more characteristics of a speaker or application associated with an audio stream.

Abstract: A visual interface to an IVR system is provided to allow an interaction between a user and an interactive voice response (IVR) system to be visually monitored. A visual representation of an audio communication with an agent is generated based on the IVR script. The commands in the IVR scripts can be mapped to a visual representation. One or more fields in the visual representation can be populated with utterances of the caller. The agent can optionally review or update a field in the visual representation that has been populated with an utterance. An agent can optionally alter a flow of the IVR script or intervene in the audio communication.

Abstract: A communication device includes a speaker, a microphone, and a processor connected to the speaker and the microphone. The processor is arranged for calculating ambient temperature by playing a test sound on the speaker, measuring a transit time of the test sound from the speaker to the microphone, and determining the ambient temperature from the measured transit time. A method of calculating ambient temperature by using a communications device having a speaker, a microphone and a processor is also disclosed. The method can be used for monitoring ambient temperatures of machinery and for detecting fire conditions.

Abstract: A method and apparatus are provided for translating a classification system in a source language into one or more additional target languages. The classification system employs a sample response repository to learn to classify a communication into one of a plurality of predefined categories. The sample response repository comprises a plurality of prior communications each having a classification. The present invention translates the sample response repository using a mechanical translation process to generate a translated response repository. A natural language understanding process is then applied to the translated response repository to generate a natural language understanding module that can classify a communication in the target language. The natural language understanding process can employ statistical methods or a rule-base of classification rules that determine how communications are classified.

Abstract: The present invention provides a more accurate estimate as to time for completion of a call by using estimated time durations of separate phases of the call and by determining what phase a call is currently on. An important feature of the present invention is the use of automated speech processing techniques to estimate where the customer and agent are in their conversation and to gauge the rate of progress of the call.