System and method for identifying a speaker's community of origin from a sound sample

A method for determining a target speaker's community of origin from a sound sample of the target speaker comprising the following steps:

• identifying a standard text with known morpheme breaks;
• presenting said standard text to one or more individuals from a plurality of communities of origin;
• recording each of said individuals reading the standard text;
• segmenting each recording into morphemes along the known morpheme breaks;
• indexing each recording segment;
• adding each indexed segment to a database;
• recording a sound sample of the target speaker;
• dividing the sound sample into target speaker morpheme segments;
• indexing each target speaker morpheme segment;
• comparing the target speaker morpheme segment against the indexed recordings in the database to determine a match;
• and
• retrieving the community of origin information associated with the matched recording.

A system for determining a community of origin of a target speaker from a sound sample of the target speaker comprising:

• an indexed database comprising a plurality of indexed morpheme segments derived from segmented recordings of a number of individuals from a number of communities of origin reading a standardized text with known morpheme breaks, wherein each recording is segmented along said known morpheme breaks to generate said indexed morpheme segments;
• a recording device configured to record a sound sample of the target speaker;
• and
• a processor comprising executable software instructions, which when executed, configure the processor to divide the recorded sound sample into target speaker morpheme segments, index each target speaker morpheme segment, compare each of the target speaker morpheme segments against each of the indexed recordings in the database to determine a match, and retrieve the community of origin information associated with the matched recording.