Speech recognition system which displays a subject for recognizing an an inputted voice

A speech recognition system for recognizing an inputted voice, comprising:

• recognitive-word storage means for storing therein words which are subjects for the recognition of the currently inputted voice;
• speech recognition means for recognizing the obtaining of a word which is the most similar to said inputted voice from among all the recognitive subject words stored in said recognitive-word storage means, on the basis of a feature of said inputted voice, so as to deliver the obtained word as a recognized result;
• word storage means for storing therein words which may possibly become subjects for the recognition of the inputted voice;
• display means for automatically displaying the words stored in the second-mentioned word storage means, in order to assist a user of said speech recognition system in entering a voice input;
• and
• display-word extraction means for extracting words recently displayed among the words which have been displayed up to the present by said display means, as the words to become said recognitive subject words, so as to store the extracted words in said recognitive-word storage means.

A computer-readable storage medium storing therein a program for causing a computer to execute:

• a first procedure for obtaining a word which is the most similar to an inputted voice from among all recognitive subject words that are subjects for recognition and that are stored in recognitive-word storage means for storing therein the recognitive subject words for the recognition of the currently inputted voice, on the basis of a feature of said inputted voice, so as to deliver the most similar word as a recognized result;
• a second procedure for automatically displaying words stored in word storage means for storing therein the words which may possibly become subjects for recognition of input voices, in order to assist a user of a speech recognition system in entering a voice input;
• and
• a third procedure for extracting words recently displayed among the words which have been displayed up to the present by said second procedure, as the words to become said recognitive subject words, so as to store the extracted words in the recognitive-word storage means.

In a speech recognition system for recognizing an inputted voice, a recognitive-subject displaying method comprising the steps:

• the first step of storing words which are subjects for recognition of the inputted voice;
• the second step of obtaining a word which is the most similar to said inputted voice from among all the stored recognitive subject words, on the basis of a feature of said inputted voice, so as to deliver the most similar word as a recognized result;
• and
• the third step of automatically displaying said stored words in order to assist a user of the speech recognition system in entering a voice input.

A speech recognition method comprising the steps:

• the first step of obtaining a word which is the most similar to an inputted voice from among all recognitive subject words being subjects for recognition of the currently inputted voice, on the basis of a feature of said inputted voice, so as to deliver the most similar word as a recognized result;
• the second step of automatically displaying words stored in word storage means for storing therein the words which may possibly become subjects for recognition of input voices, in order to assist a user of a speech recognition system in entering a voice input;
• and
• the third step of extracting words recently displayed among words which have been displayed up to the present by said second step, as the words to become the recognitive subject words, so as to store the extracted words in recognitive-word storage means.