"This disclosure is directed generally to methods and apparatus for normalizing tokens found in text input prior to attempting to match those tokens to a database of names (e.g., a contact list). In various implementations, a set of suffix tuples, which may be optionally annotated, may be used to normalize tokens found in text obtained from, for instance, a user speaking into a microphone of a mobile phone or smart watch. For example, a suffix tuple,may indicate that the suffix “u” may be replaced by the suffix “a” to normalize a name, and that the resulting normalized name should be classified and/or annotated as “feminine.” Thus, for example, the spoken name “Annu” may be changed to “Anna” and labelled as “feminine.”"

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.