Speech recognizing apparatus

1. A speech recognizing apparatus comprising:

a speech start instructing section for receiving a non-verbal instruction to start speech recognition;

a speech input section for receiving uttered speech and for converting it to a speech signal;

a speech recognizing section for recognizing the speech on the basis of the speech signal delivered from the speech input section;

an utterance start time detecting section for detecting a duration of time starting when the speech start instructing section instructs to start the speech recognition and concluding when a speech signal is first delivered from the speech input section after the instruction to start speech recognition is received;

an utterance timing deciding section for deciding utterance timing indicating whether an utterance start is quick or slow by comparing the duration detected by the utterance start time detecting section with a prescribed threshold;

a speech recognition score correcting section for correcting a speech recognition score of words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section;

a score cutoff deciding section for deciding whether to provide a recognition result or not in accordance with the speech recognition score corrected by the speech recognition score correcting section;

an interaction control section for determining, in accordance with the decision result of the score cutoff deciding section, a content to be shown when exhibiting the recognition result of the speech recognizing section;

a system response generating section for generating a system response on the basis of the content to be shown determined by the interaction control section; and

an output section for outputting the system response generated by the system response generating section.

2. The speech recognizing apparatus according to claim 1 , further comprising:

a running state detecting section for detecting a running state, wherein

the speech recognition score correcting section corrects the speech recognition score of the words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section and the running state detected by the running state detecting section.

3. The speech recognizing apparatus according to claim 2 , wherein

the running state detecting section is composed of a location detecting unit for detecting the present position and for outputting as position information; and

the speech recognition score correcting section corrects the speech recognition score of the words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section and the running state or driving operation state decided on the basis of the position information output from the location detecting unit.

4. The speech recognizing apparatus according to claim 2 , wherein

the running state detecting section is composed of an acceleration detecting unit for detecting acceleration; and

the speech recognition score correcting section corrects the speech recognition score of the words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section and the running state and driving operation state decided on the basis of the acceleration detected by the acceleration detecting unit.

5. The speech recognizing apparatus according to claim 2 , wherein

the running state detecting section is composed of a location detecting unit for detecting the present position and for outputting as position information, and an acceleration detecting unit for detecting acceleration; and

the speech recognition score correcting section corrects the speech recognition score of the words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section, the running state decided on the basis of the position information output from the location detecting unit, and the driving operation state decided on the basis of the acceleration detected by the acceleration detecting unit.

6. The speech recognizing apparatus according to claim 1 , further comprising:

an in-vehicle equipment operation state collecting section for collecting an operation state of in-vehicle equipment via an onboard network, wherein

the speech recognition score correcting section corrects the speech recognition score of the words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section and the operation state of the in-vehicle equipment collected by the in-vehicle equipment operation state collecting section.

7. The speech recognizing apparatus according to claim 1 , further comprising:

a driving operation detecting section for detecting a driving operation state, wherein

the speech recognition score correcting section corrects the speech recognition score of the words recognized by the speech recognizing section in accordance with the utterance timing decided by the utterance timing deciding section and the driving operation state detected by the driving operation detecting section.

8. A speech recognizing apparatus comprising:

a speech start instructing section for receiving a non-verbal instruction to start speech recognition;

a speech input section for receiving uttered speech and for converting it to a speech signal;

a speech recognizing section for recognizing the speech on the basis of the speech signal delivered from the speech input section;

an utterance start time detecting section for detecting a duration starting when the speech start instructing section instructs to start the speech recognition and concluding when a speech signal is first delivered by the speech input section after the instruction to start speech recognition is first received;

a variance considering utterance timing learning section for calculating an utterance timing decision threshold considering a variance on the basis of durations detected by the utterance start time detecting section in plural times of past trials;

an utterance timing deciding section for deciding the utterance timing indicating whether an utterance start is quick or slow by comparing the utterance timing decision threshold, which is calculated by the variance considering utterance timing learning section and is used as a prescribed threshold, with the duration detected by the utterance start time detecting section;

an interaction control section for determining a content, which is to be shown when exhibiting a recognition result of the speech recognizing section, in accordance with the utterance timing decided by the utterance timing deciding section;

a system response generating section for generating a system response on the basis of the content to be shown determined by the interaction control section;

an output section for outputting the system response generated by the system response generating section; and

a correction key for instructing to cancel the recognition result by the speech recognizing section, wherein

the variance considering utterance timing learning section calculates the utterance timing decision threshold considering the variance on the basis of the durations detected by the utterance start time detecting section in plural times of past trials and on the basis of duration from a time when the output section outputs the system response to a time when the correction key instructs canceling.