1. A rear wheel toe angle control device for a vehicle including a pair of rear wheels, comprising:
a toe angle actuator for changing a toe angle of each rear wheel;
a cornering power detecting unit for determining a cornering power of each rear wheel; and
a control unit for controlling the toe angle actuator;
wherein, when a reduction in the cornering power of one of the rear wheels is determined by the cornering power detecting unit, the control unit changes the toe angle of the other rear wheel in a direction to increase a slip angle of the other rear wheel.
2. The rear wheel toe angle control device according to claim 1, wherein, when a reduction in the cornering power of one of the rear wheels is determined by the cornering power detecting unit, the control unit additionally changes the toe angle of the one rear wheel in a direction to decrease the slip angle of the one rear wheel.
3. The rear wheel toe angle control device according to claim 1, wherein the cornering power detecting unit comprises at least a member of a group consisting of an air pressure sensor for detecting an air pressure of a pneumatic tire of each rear wheel and a tire kind determining unit for determining a kind of a tire fitted to each of the rear wheels.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method comprising:
recognizing untranscribed audio utterances that are candidates for transcription using a trained acoustic model and a trained language model;
computing confidence scores associated with an accuracy of speech recognition of the untranscribed audio utterances; and
transcribing an audio utterance from the untranscribed audio utterances, the audio utterance having a lowest confidence score in the confidence scores.
2. The method of claim 1, further comprising iteratively repeating the transcribing with additional audio utterances from the untranscribed audio utterances until a word accuracy converges.
3. The method of claim 1, further comprising removing the audio utterance which was transcribed from a database comprising the untranscribed audio utterances.
4. The method of claim 1, wherein the audio utterance comprises a plurality of audio works.
5. The method of claim 1, further comprising leaving out from consideration for transcription utterances with confidence scores indicating that the untranscribed audio utterances were correctly recognized.
6. The method of claim 1, wherein word posterior probability estimates are used for the confidence scores associated with the untranscribed audio utterances.
7. The method of claim 6, wherein a word is considered to be correctly recognized when an associated posterior probability is higher than a second threshold value.
8. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
recognizing untranscribed audio utterances that are candidates for transcription using a trained acoustic model and a trained language model;
computing confidence scores associated with an accuracy of speech recognition of the untranscribed audio utterances; and
transcribing an audio utterance from the untranscribed audio utterances, the audio utterance having a lowest confidence score in the confidence scores.
9. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in operations comprising iteratively repeating the transcribing with additional audio utterances from the untranscribed audio utterances until a word accuracy converges.
10. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in operations comprising removing the audio utterance which was transcribed from a database comprising the untranscribed audio utterances.
11. The system of claim 8, wherein the audio utterance comprises a plurality of audio works.
12. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in operations comprising leaving out from consideration for transcription utterances with confidence scores indicating that the untranscribed audio utterances were correctly recognized.
13. The system of claim 8, wherein word posterior probability estimates are used for the confidence scores associated with the untranscribed audio utterances.
14. The system of claim 13, wherein a word is considered to be correctly recognized when an associated posterior probability is higher than a second threshold value.
15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
recognizing untranscribed audio utterances that are candidates for transcription using a trained acoustic model and a trained language model;
computing confidence scores associated with an accuracy of speech recognition of the untranscribed audio utterances; and
transcribing an audio utterance from the untranscribed audio utterances, the audio utterance having a lowest confidence score in the confidence scores.
16. The computer-readable storage device of claim 15, having additional instructions stored which result in operations comprising iteratively repeating the transcribing with additional audio utterances from the untranscribed audio utterances until a word accuracy converges.
17. The computer-readable storage device of claim 15, having additional instructions stored which result in operations comprising removing the audio utterance which was transcribed from a database comprising the untranscribed audio utterances.
18. The computer-readable storage device of claim 15, wherein the audio utterance comprises a plurality of audio works.
19. The computer-readable storage device of claim 15, having additional instructions stored which result in operations comprising leaving out from consideration for transcription utterances with confidence scores indicating that the untranscribed audio utterances were correctly recognized.
20. The computer-readable storage device of claim 19, wherein word posterior probability estimates are used for the confidence scores associated with the untranscribed audio utterances.