Abstract: A speech recognition device is a speech recognition device for performing speech recognition using an end-to-end model and includes an encoder that is a model that converts an input speech signal into a characteristic expression, a decoder that is a model that converts speech data into text using an output of the encoder, and a learning unit that randomly selects a block length of the speech signal input to the encoder and causes the encoder and the decoder to learn.

Abstract: A speech recognition device includes: an acquisition part, acquiring a speech signal; a speech feature amount calculation part, calculating a speech feature amount; a first speech recognition part, based on the speech feature amount, performing speech recognition using a learned first E2E model, attaching a first tag to a vocabulary portion of a specific class in text that is a recognition result, and outputting the same; a second speech recognition part, based on the speech feature amount, performing speech recognition using a learned second E2E model, attaching a second tag to a vocabulary portion of a specific class in a phoneme that is a recognition result, and outputting the same; a phoneme replacement part, replacing a vocabulary with the first tag with a phoneme with the second tag; and an output part, converting the phoneme with the second tag into text and outputting the same.

Abstract: The speech recognition that is disclosed analyzes an acoustic feature for each subframe of an audio signal; provides a first model configured to determine a hidden state for each frame consisting of multiple subframes on the basis of the acoustic feature; provides a second model configured to determine a hidden state for each frame consisting of multiple subframes on the basis of the acoustic feature; and provides a third model configured to determine an utterance content on the basis of a sequence of the hidden states of each block consisting of multiple frames belonging to a voice segment.

Abstract: In detecting abnormal sound of a test object such as a vehicle immediately after completion of vehicle assembly, a reference sound data is recorded as reference data having phase and amplitude in each of multiple frequency bands reference sounds of types not previously recorded as abnormal sounds in the test object similar to the test object, test sound data is acquired which has phase and amplitude in the multiple frequency bands from test sounds generated by the test object. And sound feature data is acquires by comparing the test sound data with reference sound data in frequency bands the same as the multiple frequency bands and by changing amplitude of the test sound data based on amplitude of the reference sound data while maintaining phase of the test sound data, and abnormal sound is detected based on the acquired sound feature data.

Abstract: In determining presence/absence of abnormal sound occurrence in a test object such as a vehicle immediately after completion of vehicle assembly, sound data of the test object during running on a rough test track is recorded and resolved into multiple frequency bands by time unit. The sound data resolved into multiple frequency bands by time unit is compared among the multiple frequency bands and correlation coefficients matrix values indicating strength of correlation between the multiple frequency bands n are calculated. Presence/absence of the abnormal sound occurrence is finally determined based on the calculated correlation coefficients matrix values.

Abstract: In detecting abnormal sound of a test object such as a vehicle immediately after completion of vehicle assembly, a reference sound data is recorded as reference data having phase and amplitude in each of multiple frequency bands reference sounds of types not previously recorded as abnormal sounds in the test object similar to the test object, test sound data is acquired which has phase and amplitude in the multiple frequency bands from test sounds generated by the test object. And sound feature data is acquires by comparing the test sound data with reference sound data in frequency bands the same as the multiple frequency bands and by changing amplitude of the test sound data based on amplitude of the reference sound data while maintaining phase of the test sound data, and abnormal sound is detected based on the acquired sound feature data.

Abstract: In determining presence/absence of abnormal sound occurrence in a test object such as a vehicle immediately after completion of vehicle assembly, sound data of the test object during running on a rough test track is recorded and resolved into multiple frequency bands by time unit. The sound data resolved into multiple frequency bands by time unit is compared among the multiple frequency bands and correlation coefficients matrix values indicating strength of correlation between the multiple frequency bands n are calculated. Presence/absence of the abnormal sound occurrence is finally determined based on the calculated correlation coefficients matrix values.