Generation device, recognition system, and generation method for generating finite state transducer

A recognition system comprising a generation device and a recognition device, wherein

• the generation device includes
• a receiving unit that receives a model which converts one or more phonetic symbols into words, and
• a generating unit that generates a first finite state transducer based on the model, the first finite state transducer at least including, as outgoing transitions from a first state representing transition destination of a first transition which has a first phonetic symbol of a predetermined type as input symbol,
• a second transition that has a second phonetic symbol, which is different than the first phonetic symbol, as input symbol, and
• a third transition that has a third phonetic symbol, which represents the first phonetic symbol or silence, as input symbol, and
• the recognition device includes
• a searching unit that refers to the first finite state transducer and recognizes a word corresponding to an input speech.

A generation method for generating finite state transducer, comprising:

• receiving a model representing correspondence between one or more phonetic symbols and one or more words;
• and
• generating a first finite state transducer based on the model, the first finite state transducer at least including, as outgoing transitions from a first state representing transition destination of a first transition which has a first phonetic symbol of a predetermined type as input symbol,
• a second transition that has a second phonetic symbol, which is different than a particular symbol representing part or whole of input symbol of the first transition, as input symbol, and
• a third transition that has a third phonetic symbol, which represents the particular symbol or silence, as input symbol.