Abstract: During a conversation over the network, a microphone attachable to or included in a mobile computer system is used to input audio speech from the user of the computer system. The audio speech is processed into audio speech data. In the audio speech data, the processor monitors for a keyword previously defined by the user. Upon detecting the keyword in the audio speech data, a contextual portion of the audio speech data is extracted including the keyword. The contextual portion of the audio speech data may be converted to text and stored in memory of the computer system or on the network.