Correction of matching results for speech recognition

A speech recognition program stored in a non-transitory computer-readable recording medium that allows a computer to execute:

• feature calculation processing that converts an input sound signal into a feature for each frame;
• sound level calculation processing that calculates an input sound level expressed as power or an amplitude of the sound signal in each frame;
• decoding processing that receives the feature of each frame calculated by the feature calculation processing, matches the feature with an acoustic model and a linguistic model recorded in advance, and outputs a recognized word sequence based on the matching results, the acoustic model being data obtained by modeling of what feature speech is likely to have, and the linguistic model being data relating to a recognition word;
• start-point detection processing that compares the input sound level calculated by the sound level calculation processing with a reference value to determine a start frame serving as a start point of a speech section;
• end-point detection processing that compares the input sound level calculated by the sound level calculation processing with a reference value to determine an end frame serving as an end point of the speech section;
• and
• reference value updating processing that updates the reference value in accordance with variations in the input sound level after the start frame,
• wherein when the reference value is updated by the reference value updating processing, the start frame is updated using the updated reference value by the start-point detection processing, and
• when matching is started by the decoding processing and then the start frame is updated by the start-point detection processing after the matching is started and before the end frame is determined by the end-point detection processing, the already existing matching results by the decoding processing are corrected in accordance with the updated start frame by the decoding processing.

A speech recognition method executed by a processor comprising:

• calculating, by the processor, a feature by converting an input sound signal into a feature for each frame;
• calculating, by the processor, an input sound level expressed as power or an amplitude of the sound signal in each frame;
• decoding, by the processor, the feature of each frame by receiving the feature of each frame, matching the feature with an acoustic model and a linguistic model recorded in advance, and outputting a recognized word sequence based on the matching results, the acoustic model being data obtained by modeling of what feature speech is likely to have, and the linguistic model being data relating to a recognition word;
• determining, by the processor, a start frame serving as a start point of a speech section by comparing the input sound level with a reference value;
• determining, by the processor, an end frame serving as an end point of the speech section by comparing the input sound level with a reference value;
• and
• updating, by the processor, the reference value in accordance with variations in the input sound level after the start frame,
• wherein when the reference value is updated, the start frame is updated using the updated reference value, and
• when matching is started and then the start frame is updated after the matching is started and before the end frame is determined, the already existing matching results are corrected in accordance with the updated start frame.