Generalized phrases in automatic speech recognition systems
A method for generating a suggested phrase having a similar meaning to a supplied phrase in an analytics system includes: receiving, on a computer system comprising a processor and memory storing instructions, the supplied phrase, the supplied phrase including one or more terms; identifying, on the computer system, a term of the phrase belonging to a semantic group; generating the suggested phrase using the supplied phrase and the semantic group; and returning the suggested phrase.
1. A method for generating a generalized phrase based on a plurality of supplied phrases in an analytics system, the method comprising:
receiving, on a computer system comprising a processor and memory storing instructions, the plurality of supplied phrases, the plurality of supplied phrases comprising one or more terms, the computer system storing a plurality of categories, each of the plurality of categories having a different topic and the plurality of supplied phrases each having a meaning semantically related to the topic;
identifying, on the computer system, a term of the plurality of supplied phrases belonging to a semantic group representing a plurality of terms having equivalent semantic meaning;
identifying, on the computer system, a category of the plurality of categories based on a semantic similarity between the plurality of supplied phrases and the topic of the identified category;
generating the generalized phrase using the plurality of supplied phrases, the identified category, and the semantic group, the generating comprising replacing the term of the plurality of supplied phrases with the semantic group, the generalized phrase representing the plurality of supplied phrases having a similar meaning to the plurality of supplied phrases, wherein the generalized phrase has been determined by comparing the generalized phrase to the plurality of supplied phrases and removing duplicate phrases to obtain a generalized phrase; and
returning the generalized phrase.
2. The method of claim 1 , wherein the semantic group is a formal grammar.
3. The method of claim 2 , wherein the formal grammar is configured to match one of an amount of money, a date, a time, a telephone number, a credit card number, a social security number, a zip code, and a zip code.
4. The method of claim 1 , wherein the semantic group comprises a plurality of terms.
5. The method of claim 4 , wherein the semantic group is generated by:
computing differences between each of a plurality of phrases generated by an automatic speech recognition engine, each of the plurality of phrases comprising a plurality of terms;
grouping the plurality of phrases by similarity;
identifying locations of differences between the plurality of phrases; and
defining a generalized semantic group, the generalized semantic group comprising terms at the locations of the differences in the plurality of phrases.
6. The method of claim 1 , wherein the generalized phrase is supplied as training data to a speech recognition system.
7. The method of claim 1 , wherein the analytics system is a speech analytics system.
8. A system comprising:
a processor; and
a memory, wherein the memory stores:
a plurality of categories, each of the plurality of categories having a different topic and a plurality of phrases each having a meaning semantically related to the different topic; and
instructions that, when executed by the processor, causes the processor to:
receive a plurality of supplied phrases, the plurality of supplied phrases comprising one or more terms;
identify a term of the plurality of supplied phrases belonging to a semantic group representing a plurality of terms having equivalent semantic meaning;
identify a category of the plurality of categories based on a semantic similarity between the plurality of supplied phrases and the different topic of the identified category;
generate a generalized phrase using the plurality of supplied phrases, the identified category, and the semantic group, including replacing the term of the plurality of supplied phrases with the semantic group, the generalized phrase representing the plurality of supplied phrases having a similar meaning to the plurality of supplied phrases, wherein the generalized phrase has been determined by comparing the generalized phrase to the plurality of phrases and removing duplicate phrases to obtain a generalized phrase; and
return the generalized phrase.
9. The system of claim 8 , wherein the semantic group is a formal grammar.
10. The system of claim 9 , wherein the formal grammar is configured to match one of an amount of money, a date, a time, a telephone number, a credit card number, a social security number, a zip code, and a zip code.
11. The system of claim 8 , wherein the semantic group comprises a plurality of terms.
12. The system of claim 11 , wherein the memory stores instructions to cause the processor to generate the semantic group generated by:
computing differences between each of the plurality of supplied phrases generated by an automatic speech recognition engine, each of the plurality of supplied phrases comprising a plurality of terms;
grouping the plurality of supplied phrases by similarity;
identifying locations of differences between the plurality of supplied phrases; and
defining a generalized semantic group, the generalized semantic group comprising terms at the locations of the differences in the plurality of supplied phrases.
13. The system of claim 8 , wherein the generalized phrase is supplied as training data to a speech recognition system.
14. The system of claim 8 , wherein the processor and memory are components of a speech analytics system.