Method of determining end point detection time and electronic device for performing the method
A method of determining an End Point Detection (EPD) time and an electronic device for performing the method are provided. The electronic device includes a processor and a memory electrically connected to the processor and configured to store commands executed by the processor. The processor may be configured to recognize an utterance when the commands are executed, determine an End Point Detection (EPD) time for terminating recognition of the utterance based on utterance data stored in the memory, and terminate the recognition of the utterance when the utterance is not additionally input within the EPD time. The utterance data may include sentence data, which includes a pattern related to a sentence type of the utterance, and word data, which includes a word of the utterance.
1 . An electronic device comprising:
memory storing instructions; and
at least one processor communicatively coupled to the memory,
wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to:
recognize an utterance that is input,
determine an End Point Detection (EPD) time for terminating recognition of the utterance, based on a result of comparing a pattern of the utterance to utterance data stored in the memory,
when the utterance is not additionally input within the EPD time, terminate the recognition of the utterance,
determine a user input based on the recognized utterance,
based on the recognition of the utterance being terminated, perform at least one operation based on the determined user input, and
provide at least one of a visual output via a display or a sound output via a speaker, based on the at least one operation being performed, and
wherein the utterance data comprises:
sentence data, which comprises a pattern related to a sentence type of the utterance, and
word data, which comprises a word of the utterance.
2 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine a category of the utterance, and
determine the EPD time, using the sentence data and the word data corresponding to the category.
3 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine whether the pattern of the utterance is substantially the same as the pattern of the utterance data, and
determine the EPD time according to whether the utterance is substantially the same as the pattern.
4 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine whether the pattern of the utterance is similar to the pattern of the utterance data, and
determine the EPD time according to whether the utterance is similar to the pattern.
5 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine the EPD time based on a frequency of the pattern of the utterance.
6 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine whether the utterance is a complete sentence, using the utterance and the utterance data, and
determine the EPD time according to whether the utterance is the complete sentence.
7 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine whether the utterance is an incomplete sentence, using the utterance and the utterance data, and
determine the EPD time according to whether the utterance is the incomplete sentence.
8 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
identify whether the utterance comprises an EPD command, which is preset, and
determine the EPD time according to the EPD command.
9 . The electronic device of claim 1 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
update the utterance data according to a preset update criterion.
10 . The electronic device of claim 1 ,
wherein a plan for performing the at least one operation is generated or selected by an artificial intelligence (AI) system based on the determined user input, and
wherein the at least one operation is performed based on the plan.
11 . An electronic device comprising:
memory storing instructions; and
at least one processor communicatively coupled to the memory,
wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to:
recognize an utterance that is input,
determine a category of the utterance,
compare a pattern of the utterance to a pattern of utterance data corresponding to the category that is stored in the memory,
when the pattern of the utterance is different from the pattern of the utterance data, determine whether the utterance is a complete sentence, an incomplete sentence, or an ambiguous sentence,
determine an End Point Detection (EPD) time for terminating recognition of the utterance, based on at least one of a result of the comparing of the pattern of the utterance to the pattern of the utterance data, or whether the utterance is the complete sentence, the incomplete sentence, or the ambiguous sentence,
when the utterance is not additionally input within the EPD time, terminate the recognition of the utterance,
determine a user input based on the recognized utterance,
based on the recognition of the utterance being terminated, perform at least one operation based on the determined user input, and
provide at least one of a visual output via a display or a sound output via a speaker, based on the at least one operation being performed, and
wherein the utterance data comprises:
sentence data, which comprises the pattern related to a sentence type of the utterance, and
word data, which comprises a word of the utterance.
12 . The electronic device of claim 11 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine whether the pattern of the utterance is substantially the same as the pattern of the utterance data, and
determine the EPD time according to whether the utterance is substantially the same as the pattern.
13 . The electronic device of claim 11 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to:
determine whether the pattern of the utterance is similar to the pattern of the utterance data, and
determine the EPD time according to whether the utterance is similar to the pattern.
14 . The electronic device of claim 11 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the electronic device to;
determine the EPD time based on a frequency of the pattern of the utterance.
15 . The electronic device of claim 11 ,
wherein a plan for performing the at least one operation is generated or selected by an artificial intelligence (AI) system based on the determined user input, and
wherein the at least one operation is performed based on the plan.
16 . A method performed by an electronic device, the method comprising:
recognizing an utterance that is input;
determining an End Point Detection (EPD) time for terminating recognition of the utterance, based on a result of comparing a pattern of the utterance to utterance data stored in a memory of the electronic device;
when the utterance is not additionally input within the EPD time, terminating the recognition of the utterance;
determining a user input based on the recognized utterance;
based on the recognition of the utterance being terminated, performing at least one operation based on the determined user input; and
providing at least one of a visual output via a display or a sound output via a speaker, based on the at least one operation being performed,
wherein the utterance data comprises:
sentence data, which comprises a pattern related to a sentence type of the utterance, and
word data, which comprises a word of the utterance.
17 . The method of claim 16 , further comprising
determining a category of the utterance,
wherein the determining of the EPD time comprises determining the EPD time, using the sentence data and the word data corresponding to the category.
18 . The method of claim 16 , wherein the determining of the EPD time comprises:
determining whether the pattern of the utterance is substantially the same as the pattern of the utterance data; and
determining the EPD time according to whether the utterance is substantially the same as the pattern.
19 . The method of claim 16 , wherein the determining of the EPD time comprises:
determining whether the pattern of the utterance is similar to the pattern of the utterance data; and
determining the EPD time according to whether the utterance is similar to the pattern.
20 . The method of claim 16 ,
wherein a plan for performing the at least one operation is generated or selected by an artificial intelligence (AI) system based on the determined user input, and
wherein the at least one operation is performed based on the plan.