Communication skill evaluation system, device, method, and program

A communication skill evaluation device comprising:

• a hardware processor that:
• detects, based on audio information of participants in a conversation, an utterance period defined by starting and ending times of each utterance in the conversation, and a participant who spoke in each detected utterance period;
• defines, as an utterance pair, two utterances obtained in chronological order from each detected utterance period;
• assigns, in accordance with whether or not each of the participants spoke in each defined utterance pair, a participatory role to each of the participants, the participatory role indicating that a participant is one of a current speaker who is speaking when the speaker is continuing, a non-speaker who is not the current speaker when the speaker is continuing, a current speaker who stops speaking when the speaker changes, a next speaker who speaks next when the speaker changes, and a non-speaker who is neither the current speaker nor the next speaker when the speaker changes;
• extracts, based on measurement results of non-verbal action of each of the participants during the conversation, a non-verbal feature quantity for each of the participants, relating to the non-verbal action at the end of the utterance in each detected utterance period;
• and
• estimates communication skill for each of the participants based on a combination, in each detected utterance period, of the assigned participatory role and the extracted non-verbal feature quantity.

A communication skill evaluation method comprising:

• detecting, based on audio information of participants in a conversation, an utterance period defined by starting and ending times of each utterance in the conversation, and a participant who spoke in each detected utterance period;
• defining, as an utterance pair, two utterances obtained in chronological order from each detected utterance period;
• assigning, in accordance with whether or not each of the participants spoke in each defined utterance pair, a participatory role to each of the participants, the participatory role indicating that a participant is one of a current speaker who is speaking when the speaker is continuing, a non-speaker who is not the current speaker when the speaker is continuing, a current speaker who stops speaking when the speaker changes, a next speaker who speaks next when the speaker changes, and a non-speaker who is neither the current speaker nor the next speaker when the speaker changes;
• extracting, based on measurement results of non-verbal action of each of the participants during the conversation, a non-verbal feature quantity for each of the participants, relating to the non-verbal action at the end of the utterance in each detected utterance period;
• and
• estimating communication skill for each of the participants based on a combination, in each detected utterance period, of the assigned participatory role and the extracted non-verbal feature quantity.

A communication skill evaluation system comprising:

• a hardware processor that:
• defines, as an utterance pair, two utterances obtained in chronological order from each utterance period, each utterance period being defined by starting and ending times of each utterance based on audio information representing voices of participants in a conversation;
• assigns, in accordance with whether or not each of the participants spoke in each defined utterance pair, a participatory role to each of the participants, the participatory role indicating that a participant is one of a current speaker who is speaking when the speaker is continuing, a non-speaker who is not the current speaker when the speaker is continuing, a current speaker who stops speaking when the speaker changes, a next speaker who speaks next when the speaker changes, and a non-speaker who is neither the current speaker nor the next speaker when the speaker changes;
• and
• estimates communication skill for each one of the participants based on a combination, in each utterance period, of the participatory role assigned to the one of the participants and a non-verbal feature quantity indicating a non-verbal action of the one of the participants at the end of the utterance in the utterance period.

A communication skill evaluation device comprising:

• a hardware processor that:
• defines, as an utterance pair, two utterances obtained in chronological order from each utterance period, each utterance period being defined by starting and ending times of each utterance based on audio information representing voices of participants in a conversation;
• assigns, in accordance with whether or not each of the participants spoke in each defined utterance pair, a participatory role to each of the participants, the participatory role indicating that a participant is one of a current speaker who is speaking when the speaker is continuing, a non-speaker who is not the current speaker when the speaker is continuing, a current speaker who stops speaking when the speaker changes, a next speaker who speaks next when the speaker changes, and a non-speaker who is neither the current speaker nor the next speaker when the speaker changes;
• and
• estimates communication skill for each one of the participants based on a combination, in each utterance period, of the participatory role assigned to the one of the participants and a non-verbal feature quantity indicating a non-verbal action of the one of the participants at the end of the utterance in the utterance period.

A communication skill evaluation method comprising:

• defining, as an utterance pair, two utterances obtained in chronological order from each utterance period, each utterance period being defined by starting and ending times of each utterance based on audio information representing voices of participants in a conversation;
• assigning, in accordance with whether or not each of the participants spoke in each utterance pair, a participatory role to each of the participants, the participatory role indicating that a participant is one of a current speaker who is speaking when the speaker is continuing, a non-speaker who is not the current speaker when the speaker is continuing, a current speaker who stops speaking when the speaker changes, a next speaker who speaks next when the speaker changes, and a non-speaker who is neither the current speaker nor the next speaker when the speaker changes;
• and
• estimating communication skill for each one of the participants based on a combination, in each utterance period, of the participatory role assigned to the one of the participants and a non-verbal feature quantity indicating a non-verbal action of the one of the participants at the end of the utterance in the utterance period.