Voice recognition performance estimation apparatus, method and program allowing insertion of an unnecessary word

A voice recognition estimating method, comprising:

• generating properties of estimation voice data used to determine, based on an estimation item, a feature of synthetic voice data, the estimation item being used to estimate performance of a voice recognition apparatus;
• generating a parameter used to generate the synthetic voice data as estimation voice data corresponding to the properties of the estimation voice data;
• generating the synthetic voice data based on the parameter;
• outputting the synthetic voice data to the voice recognition apparatus;
• acquiring a recognition result from the voice recognition apparatus, the recognition result being obtained when the voice recognition apparatus recognizes the synthetic voice data;
• and
• estimating the performance of the voice recognition apparatus with reference to the estimation item and the recognition result,
• wherein the generating the properties of the estimation voice data includes
• acquiring vocabulary data and unnecessary word data as the estimation item, the vocabulary data being used to make the synthetic voice data correspond to an actual voice indicating a word, the unnecessary word data indicating an unnecessary word inserted in the vocabulary data and an insertion position of the unnecessary word;
• storing a plurality of voice quality data items;
• selecting several voice quality data items of the voice quality data items in accordance with the estimation item;
• and
• generating the properties of the estimation voice data, the properties of the estimation voice data including the selected voice quality data items, the vocabulary data and the unnecessary word data.

A computer-readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a voice recognition estimating method, comprising:

• generating properties of estimation voice data used to determine, based on an estimation item, a feature of synthetic voice data, the estimation item being used to estimate a performance of a voice recognition apparatus;
• generating a parameter used to generate the synthetic voice data as estimation voice data corresponding to the properties of the estimation voice data;
• generating the synthetic voice data based on the parameter;
• outputting the synthetic voice data to the voice recognition apparatus;
• acquiring a recognition result from the voice recognition apparatus, the recognition result being obtained when the voice recognition apparatus recognizes the synthetic voice data;
• and
• estimating the performance of the voice recognition apparatus with reference to the estimation item and the recognition result,
• wherein the generating properties of the estimation voice data includes
• acquiring vocabulary data and unnecessary word data as the estimation item, the vocabulary data being used to make the synthetic voice data correspond to an actual voice indicating a word, the unnecessary word data indicating an unnecessary word inserted in the vocabulary data and an insertion position of the unnecessary word;
• storing a plurality of voice quality data items;
• selecting several voice quality data items of the voice quality data items in accordance with the estimation item;
• and
• generating the properties of the estimation voice data, the properties of the estimation voice data including the selected voice quality data items, the vocabulary data and the unnecessary word data.