The speaker recognition API example shows that the response is something like this. But in a long conversation, there are at least two people and there are multiple start and end of segment. Will this API return those? i.e. a list or array or start and ends against recognized speaker.
"""Response.
response = {
userId: userId of the speaker identified in the segment,
start: start of the segment,
end: end of the segment
}
"""
From https://docs.deepaffects.com/docs/speaker-diarization-api.html, it sounds like a list of segments. Each segment has javascript object shown in response above.
The speaker recognition API example shows that the response is something like this. But in a long conversation, there are at least two people and there are multiple start and end of segment. Will this API return those? i.e. a list or array or start and ends against recognized speaker.
"""Response. response = {
userId: userId of the speaker identified in the segment, start: start of the segment, end: end of the segment } """ From https://docs.deepaffects.com/docs/speaker-diarization-api.html, it sounds like a list of segments. Each segment has javascript object shown in response above.
Please confirm and update the documentation.