Back to results
US 7,689,423 B2Granted
System and method of providing telematically user-optimized configurable audio
AssigneeGeneral Motors Corporation
InventorsJames E. Bicego, Anthony J. Sumcad, Russell A. Patenaude
Life of this patent
Estimating the term…
Abstract
A method of repeating a computer recognized string in a telematics unit in a vehicle, including receiving a user utterance at the telematics unit from a user, the user utterance including a plurality of words and a plurality of user pauses between the words, parsing the user utterance into a plurality of phonemes, forming a data string in which each user pause is associated with a phoneme adjacent to the user pause, and playing back the data string.
Claims20
A method of repeating a computer recognized string in a telematics unit in a vehicle, comprising:
- receiving a user utterance at the telematics unit from a user, the user utterance including a plurality of segments including a user pause between each segment, each of the plurality of segments having a plurality of words and a plurality of user pauses between the words;
- parsing the user utterance into a plurality of phonemes;
- forming a data string, via a processor operatively associated with the telematics unit, in which each user pause is associated with a phoneme adjacent to the user pause by i) determining an average duration of each user pause between the plurality of words in each segment, ii) assigning a time duration for each of the user pauses based on the average duration determination of each user pause between the plurality of words, iii) determining an average duration of each user pause between each segment, iv) assigning a time duration for each of the user pauses based on the average duration determination of each user pause between each segment, v) associating each user pause with the phoneme adjacent to the user pause, and vi) concatenating each user pause and the associated phoneme, each user pause including its associated assigned time duration;
- generating a virtual utterance corresponding to the data string;
- and
- playing back the virtual utterance to the user.
3 more elements
A computer readable medium storing a computer program comprising:
- computer readable code for receiving a user utterance at the telematics unit from a user, the user utterance including a plurality of segments including a user pause between each segment, each of the plurality of segments having a plurality of words and a plurality of user pauses between the words;
- computer readable code for parsing the user utterance into a plurality of phonemes;
- computer readable code for forming a data string in which each user pause is associated with a phoneme adjacent to the user pause, wherein the computer readable code for forming the data string includes i) computer readable code for determining an average duration of each pause between the plurality of words in each segment, ii) computer readable code for assigning a time duration for each of the user pauses based on the average duration determination of each user pause between the plurality of words, iii) computer readable code for determining an average duration of each user pause between each segment, iv) computer readable code for assigning a time duration for each of the user pauses based on the average duration determination of each user pause between each segment, v) computer readable code for associating each pause with the phoneme adjacent to the user pause, and vi) computer readable code for concatenating each user pause and the associated phoneme, each user pause including its associated assigned time duration;
- computer readable code for generating a virtual utterance corresponding to the data string;
- and
- computer readable code for playing back the virtual utterance to the user.
3 more elements
A system of repeating a computer recognized string in a telematics unit in a vehicle, the system comprising a memory, and a processing performing the steps of:
- means for receiving a user utterance from a user, the user utterance including a plurality of segments including a user pause between each segment, each of the plurality of segments having a plurality of words and a plurality of user pauses between the words;
- means for parsing the user utterance into a plurality of phonemes;
- means for forming a data string in which each user pause is associated with a phoneme adjacent to the user pause, wherein the means for forming the data string includes i) means for determining an average duration of each pause between the plurality of words in each segment, ii) means for assigning a time duration for each of the user pauses based on the average duration determination of each user pause between the plurality of words, iii) means for determining an average duration of each user pause between each segment, iv) means for assigning a time duration for each of the user pauses based on the average duration determination of each user pause between each segment, v) means for associating each pause with the phoneme adjacent to the user pause, and vi) means for concatenating each user pause and the associated phoneme, each user pause including its associated assigned time duration;
- means for generating a virtual utterance corresponding to the data string;
- and
- means for playing back the virtual utterance to the user.
3 more elements
Dependencies are inferred from the claim text.