Abstract: A method of accessing voice services through a personal computing system can include receiving, in the personal computing system, a telephone call from a user registered with the personal computing system, wherein the user is remotely located from the personal computing system, receiving a user spoken utterance over the telephone call, and speech recognizing the user spoken utterance to determine a request for a voice service. The method further can include formatting an electronic message according to the request for a voice service and sending the electronic message over a communications network to a remote computing system in accordance with the request for a voice service. Also, the method can include processing and formatting a response received from the remote computing system and playing back audio to the user over the telephone call.

Abstract: A method of accessing voice services through a personal computing system can include receiving, in the personal computing system, a telephone call from a user registered with the personal computing system, wherein the user is remotely located from the personal computing system, receiving a user spoken utterance over the telephone call, and speech recognizing the user spoken utterance to determine a request for a voice service. The method further can include formatting an electronic message according to the request for a voice service and sending the electronic message over a communications network to a remote computing system in accordance with the request for a voice service. Also, the method can include processing and formatting a response received from the remote computing system and playing back audio to the user over the telephone call.

Abstract: A method of accessing voice services through a personal computing system can include receiving, in the personal computing system, a telephone call from a user registered with the personal computing system, wherein the user is remotely located from the personal computing system, receiving a user spoken utterance over the telephone call, and speech recognizing the user spoken utterance to determine a request for a voice service. The method further can include formatting an electronic message according to the request for a voice service and sending the electronic message over a communications network to a remote computing system in accordance with the request for a voice service. Also, the method can include processing and formatting a response received from the remote computing system and playing back audio to the user over the telephone call.

Abstract: A method for monitoring an Internet connection can include the step of detecting a connectivity problem with a household Internet connection. A problem contact point can be determined. A communication connection that is different from the household Internet connection can be established with the contact point. For example, a voice connection can be established with the contact point. A problem notification can be conveyed to the contact point through the established communication connection.

Abstract: A method (10) and system (50) for using a biometrically enabled password can include an input device (58) capable of entering a password entry and a processor (56) coupled to the input device. The processor can monitor (16 or 26) a cadence such as monitoring a keystroke signature, store the cadence of the password entry, compare (28) the cadence of a subsequent password entry with the cadence of at least one previous password entry, establish (30) a stability metric with respect to the cadences compared, and require (32) both the password entry and the cadence once the cadence meets the stability metric. The processor can require only the password entry until the stability metric for the cadence is achieved. The processor can also determine (14) if the password entry is new and optionally require (18) only the password entry to enter the system if determined as new.

Abstract: A method of monitoring for security events using a speech recognition system can include receiving a sound signal within the speech recognition system and determining at least one attribute of the sound signal. The attribute of the sound signal can be compared with one or more acoustic models associated with a security event. The method can further include identifying the sound signal as a security event according to the comparing step.

Abstract: A method of monitoring for security events using a speech recognition system can include receiving a sound signal within the speech recognition system and determining at least one attribute of the sound signal. The attribute of the sound signal can be compared with one or more acoustic models associated with a security event. The method can further include identifying the sound signal as a security event according to the comparing step.

Abstract: A solution for determining the accuracy of a speech recognition system. A first graphical user interface (GUI) is provided for selecting a transaction log. The transaction log has at least one entry that specifies a speech recognition text result. A second GUI is also provided for selecting at least one audio segment corresponding to the entry. The second GUI includes an activatable icon for initiating transcription of the audio segment through a reference speech recognition engine to generate a second text result.

Abstract: A method of determining the accuracy of a speech recognition system can include identifying from a log of the speech recognition system a text result and attributes associated with the text result. An audio representation from which the text result was derived can be accessed. The audio representation can be processed with a reference speech recognition engine to determine a second text result. The text result can be compared with the second text result to determine an accuracy of the speech recognition system.

Abstract: A method for handling an off-hook event can include the step of detecting an off-hook event with a modem communicatively linked to a circuit loop in which the off-hook event occurs. The detection can be based upon audible information conveyed within the circuit loop. At least one programmatic action can be initiated with a computing device communicatively linked to the modem. An off-hook notification can be conveyed as a result of the programmatic action.

Abstract: A solution for determining the accuracy of a speech recognition system. A first graphical user interface (GUI) is provided for selecting a transaction log. The transaction log has at least one entry that specifies a speech recognition text result. A second GUI is also provided for selecting at least one audio segment corresponding to the entry. The second GUI includes an activatable icon for initiating transcription of the audio segment through a reference speech recognition engine to generate a second text result.

Abstract: A method of determining the accuracy of a speech recognition system can include identifying from a log of the speech recognition system a text result and attributes associated with the text result. An audio representation from which the text result was derived can be accessed. The audio representation can be processed with a reference speech recognition engine to determine a second text result. The text result can be compared with the second text result to determine an accuracy of the speech recognition system.