METHOD AND DEVICE FOR SPEECH RECOGNITION

摘要

PROBLEM TO BE SOLVED: To reduce a recognition error rate based on a difference between the speaking speed of a user and an average speaking speed of an acoustic model used for speech recognition. SOLUTION: In this method and device for speech recognition, the speaking speed of the model is measured by a measuring unit 2 to reduce the error rate of the recognition result. The user is informed of this speaking speed by an output unit 3.