Voice-enabled directory look-up based on recognized spoken initial characters
First Claim
1. A method, comprising:
- capturing an audio signal representative of a plurality of spoken characters, each having a character position in one of at least two different data items;
parsing the audio signal into audio segments, each audio segment representing a character position;
decoding each audio segment into one or more candidate characters for the corresponding character position;
retrieving all directory records that contain, in a predetermined data field;
in at least one character position, either (a) one of the candidate characters, or (b) one or more substitution characters, where each substitution character is selected as a function of at least one of the candidate characters; and
in each remaining character position for which candidate characters were decoded, one of the candidate characters; and
presenting the matching records to an operator.
2 Assignments
0 Petitions
Accused Products
Abstract
A novel voice-enabled directory look-up system is disclosed. In one embodiment, an operator reads the first few characters from each of the first and last names of a mail addressee. The system captures the speech as an audio signal, which is parsed into character position segments. The system determines one or more candidate characters that might have resulted in the audio signal for each character position segment. The system then expands the list of candidate characters for at least one character position to include one or more characters that sound like the original candidate characters for that character position. The candidate characters for the respective character positions are composed into a regular expression, which is applied using an inexact string matching look-up routine to a directory of records. Records with the best matches are returned in a menu for the operator. The operator selects the desired record from the menu.
In another embodiment, an operator reads aloud the thousands and hundreds digits of the street number and the first three letters of the street name from a mail piece. A voice engine parses and decodes the speech into candidate characters for each character position. The system selects alternative characters that sound similar to candidate characters in a given character position. An inexact string matching routine retrieves records from a carrier route directory that match either a candidate character or an alternative character in each position of each data field.
161 Citations
1 Claim
-
1. A method, comprising:
-
capturing an audio signal representative of a plurality of spoken characters, each having a character position in one of at least two different data items;
parsing the audio signal into audio segments, each audio segment representing a character position;
decoding each audio segment into one or more candidate characters for the corresponding character position;
retrieving all directory records that contain, in a predetermined data field;
in at least one character position, either (a) one of the candidate characters, or (b) one or more substitution characters, where each substitution character is selected as a function of at least one of the candidate characters; and
in each remaining character position for which candidate characters were decoded, one of the candidate characters; and
presenting the matching records to an operator.
-
Specification