Electronic device and method of controlling speech recognition by electronic device

1. An electronic device comprising:

a speaker;

a microphone;

a processor; and

a memory that stores computer-readable instructions,

wherein the processor, when executing the computer-readable instructions, is configured to control the electronic device to:

receive a speech input signal through the microphone,

obtain speech output data to be output in response to the received speech input signal,

identify a specific condition for an adjustment of a speech rate of the speech output data,

generate a speech signal of the speech output data having an adjusted speech rate based at least in part on the identified specific condition, and

output the speech signal having the adjusted speech rate through the speaker,

wherein the processor, when executing the computer-readable instructions, is configured to control the electronic device to determine a text type of each word among a plurality of words included in the speech output data and generate the speech signal of the speech output data having the adjusted speech rate, and

wherein a speech rate for a predetermined text type word is adjusted to be slower than another text type word according to the determining of the text type of each word.

2. The electronic device of claim 1 , wherein the speech output data is generated by performing Automatic Speech Recognition (ASR) or Natural Language Understanding (NLU) processing on the speech input signal.

3. The electronic device of claim 2 , wherein the speech output data is generated by an external server performing the ASR or NLU processing on the speech input signal.

4. The electronic device of claim 1 , wherein the predetermined text type word includes at least one of a number, an address, an email, and a word or a sentence in a translated language.

5. The electronic device of claim 1 , wherein the processor, when executing the computer-readable instructions, is configured to control the electronic device to generate the speech signal of the speech output data having the adjusted speech rate by inserting a pause interval of a predetermined length between words or syllables included in the speech output data.

6. The electronic device of claim 1 , wherein the processor, when executing the computer-readable instructions, is configured to control the electronic device to identify a user of the electronic device from the speech input signal and generate the speech signal of the speech output data based on identity of the user.

7. A method of controlling speech recognition by an electronic device, the method comprising:

receiving a speech input signal through a microphone;

obtaining speech output data to be output in response to the received speech input signal;

identifying a specific condition for an adjustment of a speech rate of the speech output data;

determining a text type of each word among a plurality of words included in the speech output data;

generating a speech signal of the speech output data having an adjusted speech rate based at least in part on the identified specific condition; and

outputting the speech signal having the adjusted speech rate through a speaker of the electronic device,

wherein a speech rate for a predetermined text type word is adjusted to be slower than another text type word according to the determining of the text type of each word.

8. The method of claim 7 , wherein the speech output data is generated by performing Automatic Speech Recognition (ASR) or Natural Language Understanding (NLU) processing on the speech input signal.

9. The method of claim 8 , wherein the speech output data is generated by an external server performing the ASR and/or NLU processing on the speech input signal.

10. The method of claim 7 , wherein the predetermined text type word includes at least one of a number, an address, an email, and a word or a sentence in a translated language.

11. The method of claim 7 , wherein the generating comprises inserting a pause interval of a predetermined length between words or syllables included in the speech output data.

12. The method of claim 7 , further comprising:

identifying a user of the electronic device from the received speech input signal; and

generating the speech signal of the speech output data based on identity of the user.

13. A method of improving user recognition of speech output by an electronic device, the method comprising:

receiving an input speech signal of a user of the electronic device, the input speech signal comprising a query;

performing speech analysis on the input speech signal to determine a response to the query;

generating an output speech signal corresponding to the response to the query;

determining an optimal speech rate of the output speech signal for the user of the electronic device; and

outputting the output speech signal at the optimal speech rate for the user of the electronic device,

wherein the determining comprises:

identifying an address, an email address, a number, or a word in a translated language in the output speech signal; and

determining as the optimal speech rate a first speech rate for the address, the email address, the number, or the word in the translated language in the output speech signal and a second speech rate for portions of the output speech signal other than the email address, the number, or the word in the translated language in the output speech signal,

wherein the second speech rate is faster than the first speech rate.

14. The method of claim 13 , further comprising:

receiving a request for clarification of the response to the query, in response to outputting the output speech signal at the optimal speech rate for the user of the electronic device;

determining a reduced speech rate of the output speech signal for the user of the electronic device; and

outputting the output speech signal at the reduced speech rate for the user of the electronic device.

15. The method of claim 13 , wherein the determining comprises:

determining the optimal speech rate of the output speech signal for the user of the electronic device based on an age of the user of the electronic device.

16. The method of claim 13 , wherein the determining comprises:

determining the optimal speech rate of the output speech signal for the user of the electronic device based on noise in an environment of the user of the electronic device.

17. The method of claim 13 , wherein the determining comprises:

determining the optimal speech rate of the output speech signal for the user of the electronic device based on noise, an average speech output rate of the user of the electronic device or, a request for adjustment of a speech rate of the output speech signal by the user of the electronic device.

18. The method of claim 13 , wherein the determining comprises:

determining the optimal speech rate of the output speech signal for the user of the electronic device based on noise or a complexity of the output speech signal.

19. The method of claim 13 , wherein the determining comprises:

determining the optimal speech rate of the output speech signal for the user of the electronic device based on predefined data or settings or self-learning by Artificial Intelligence (AI).