International Business Machines Corporation

Gregory L Toon

Peeyush Jaiswal

Aleksas Joseph Vitenas

Kiran Mutukuru

Victor S Moore

Shailesh B Gandhi

Approaches for recording and playing back a portion of a conversation are provided. An approach includes establishing a subscriber of a recording and play back service. The approach includes recording, by a computing device, a portion of a conversation of the subscriber that occurs in a call between a first individual and a second individual. The approach additionally includes storing, by the computing device, the portion of the conversation when the call ends. The approach further includes analyzing, by the computing device, the stored portion of the conversation to detect predefined keywords. The approach also includes automatically providing the subscriber with an option to play back the stored portion of the conversation when at least one of the predefined keywords is detected during the analyzing.

Playing back portions of a recorded conversation based on keywords

Approaches for recording and playing back a portion of a telephone call are provided. An approach includes establishing a subscriber of a recording and play back service. The approach includes recording, by a computing device, a portion of a conversation of the subscriber that occurs in a call between a first telephone and a second telephone. The approach additionally includes storing, by the computing device, the portion of the conversation when the call ends. The approach further includes analyzing, by the computing device, the stored portion of the conversation to detect predefined keywords. The approach also includes automatically providing the subscriber with an option to play back the stored portion of the conversation when at least one of the predefined keywords is detected during the analyzing.

Recording and playing back portions of a telephone call

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.

Graphical user interface for determining speech recognition accuracy

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.

Growing community of inventors

Chicago, IL, United States of America

Gregory L Toon