Speech recognition device and speech recognition method

1. A speech recognition device comprising:

a speech acquirer that acquires a speech to digitize and output the speech as an original speech signal;

a speech data processor that processes the original speech signal to generate a processed speech signal;

an acoustic analyzer that analyzes the original speech signal and the processed speech signal to generate time series data on an acoustic feature;

a plurality of acoustic models corresponding to a plurality of languages each serving as a recognition target;

a speech recognizer that converts the time series data on the acoustic feature of the original speech signal into a speech label string of each language by using the acoustic model for each language to generate a determination dictionary for each language, and that performs a recognition process on the time series data on the acoustic feature of the processed speech signal by using the acoustic model and the determination dictionary for each language to calculate a recognition score for each language; and

an acoustic model switcher that determines one acoustic model from among the plurality of the acoustic models, based on the recognition score for each language calculated by the speech recognizer.

2. The speech recognition device according to claim 1 , wherein

the speech data processor generates a plurality of the processed speech signals for one original speech signal, and

the acoustic model switcher calculates an average value of a plurality of the recognition scores corresponding to the plurality of the processed speech signals for each language, and determines the acoustic model for the language having the largest average value.

3. The speech recognition device according to claim 1 , wherein

the speech data processor generates a plurality of the processed speech signals for one original speech signal, and

the acoustic model switcher compares for each language a plurality of the recognition scores corresponding to the plurality of the processed speech signals with a threshold value, and determines the acoustic model for the language having the largest number of the recognition scores that are not less than the threshold value.

4. The speech recognition device according to claim 2 , wherein

the acoustic model switcher weights for each language the recognition score according to a time when the speech acquirer acquires the original speech signal.

5. The speech recognition device according to claim 3 , wherein

the acoustic model switcher weights the recognition score according to a time when the speech acquirer acquires the original speech signal.

6. The speech recognition device according to claim 1 , wherein

the speech data processor generates the processed speech signal in which an environmental noise is superimposed on the original speech signal.

7. The speech recognition device according to claim 1 , wherein

the speech data processor generates the processed speech signal in which a frequency of the original speech signal is fixed and volume is changed.

8. The speech recognition device according to claim 1 , further comprising a dictionary generator that registers a speech uttered by a user in a user dictionary as a recognition target word of the speech recognizer, wherein

the speech acquirer acquires the speech uttered by the user for registering the speech in the user dictionary, and outputs the acquired speech as the original speech signal.

9. The speech recognition device according to claim 1 , wherein

the speech acquirer acquires the speech uttered by a vehicle occupant, and

the speech data processor generates the processed speech signal in which a noise of the vehicle is superimposed on the original speech signal.

10. A speech recognition method comprising:

processing an original speech signal, which is a digitized speech, to generate a processed speech signal;

analyzing the original speech signal and the processed speech signal to generate time series data on an acoustic feature;

by using a plurality of acoustic models corresponding to a plurality of languages each serving as a recognition target, converting the time series data on the acoustic feature of the original speech signal into a speech label string of each language to generate a determination dictionary for each language;

performing a recognition process on the time series data on the acoustic feature of the processed speech signal by using the acoustic model and the determination dictionary for each language to calculate a recognition score for each language; and

determining one acoustic model from among the plurality of the acoustic models, based on the recognition score for each language.