VOICE RECOGNITION WITH DYNAMIC FILTER BANK ADJUSTMENT BASED ON SPEAKER CATEGORIZATION

摘要

Voice recognition methods and systems are disclosed. A voice signal is obtained for an utterance of a speaker. The speaker is categorized as a male, female, or child and the categorization is used as a basis for dynamically adjusting a maximum frequency f_max and a minimum frequency f_min of a filter bank used for processing the input utterance to produce an output. Corresponding gender or age specific acoustic models are used to perform voice recognition based on the filter bank output.