▎ 摘　　要

NOVELTY - The method involves receiving a voice query that includes an action and requested media content. A transcription of the voice query is generated. The transcription is parsed to identify an entity corresponding to the textual representation of the media content. A phonetic representation of the entity is generated. The phonetic representation includes graphene of the entity, a phoneme of the entity, and an N-gram of the entity. A fuzzy candidate list comprising fuzzy candidates representing potential matches to the requested media content is generated based on the phonetic representation. The fuzzy candidate list is ranked to form a ranked fuzzy candidate list including a highest ranked fuzzy candidate corresponding to a best potential match for the requested media content. The action associated with the highest ranked fuzzy candidate is performed. USE - Method for adapting automatic speech recognition engine. ADVANTAGE - The domain adapted audio command processing module generates domain-specific fuzzy candidates that potentially match with the content being requested by the voice query, thus effectively processing dynamic domain voice queries in an automatic speech recognition (ASR) system, and hence improving the performance of the ASR system. DESCRIPTION OF DRAWING(S) - The drawing shows a block diagram illustrating the multimedia environment. 102User 104Media system 106Media device 120Content server 122Content