Speech packetizing based linguistic processing to improve voice quality

摘要

An embodiment of the present invention is a technique of establishing a telephone communication using a packet switching communications network. Digitized voice information is received from a speaker. The voice information is placed into a payload of a first packet. The first packet is transmitted to a recipient. A significance to voice quality of the voice information contained in the first packet is calculated. One or more additional packets is transmitted to the recipient containing the voice information if the significance of the voice information is above a threshold level. One or more phonemes contained in the voice information is identified. A value from memory for each identified phoneme representing the significance to voice quality of that phoneme is retrieved. The measure of significance for the voice information is set to the maximum of the values for all of the phonemes contained in the voice information.