METHOD AND APPARATUS FOR BEHAVIORAL ANALYSIS OF A CONVERSATION
A method and an apparatus for determining speaker behavior in a conversation in a call comprising an audio is provided. The apparatus includes a call analytics server comprising a processor and a memory, which performs the method. The method comprises receiving, at a call analytics server (CAS), a call audio comprising a speech of a first speaker, identifying an emotion based on the speech and identifying a sentiment based on a call text corresponding to the speech. Based on the identified emotion and sentiment, a behavior of the first speaker in the conversation is determined.
1 . A method for determining speaker behavior in a conversation in a call comprising an audio, the method comprising:
receiving, at a call analytics server (CAS), a call audio comprising a speech of a first speaker;
identifying, at the CAS, an emotion based on the speech;
identifying, at the CAS, a sentiment based on a call text, the call text corresponding to the speech; and
determining a behavior of the first speaker in the conversation based on the emotion and the sentiment.
2 . The method of claim 1 , wherein the call text is received at the CAS from an automatic speech recognition (ASR) engine.
3 . The method of claim 1 , wherein the call audio is received at the CAS in near real time, and the call text is received at the CAS near real time.
4 . The method of claim 1 , wherein the emotion comprises at least one of happy, anger, frustration, sad or neutral,
wherein the sentiment comprises at least one of positive; strongly positive, mildly positive, negative, strongly negative, mildly negative, or neutral, and
wherein the behaviour comprises at least one of polite, impolite, friendly, rude, empathetic and neutral,
wherein the determining the behavior comprises identifying a pair comprising the emotion and the sentiment, and optionally, rate of speech, speaker energy and excitement state of the speaker.
5 . The method of claim 4 , further comprising recommending a behavior for a second speaker in the audio, in response to the determined behavior of the first speaker.
6 . An apparatus for determining speaker behavior in a conversation in a call comprising an audio, the apparatus comprising:
a processor; and
a memory communicably coupled to the processor, wherein the memory comprises computer-executable instructions, which when executed using the processor, perform a method comprising:
receiving, at a call analytics server (CAS), a call audio comprising a speech of a first speaker,
identifying, at the CAS, emotion based on the speech,
identifying, at the CAS, sentiment based on a call text, the call text corresponding to the speech, and
determining a behavior of the first speaker in the conversation based on the emotion and the sentiment.
7 . The apparatus of claim 6 , wherein the call text is received at the CAS from an automatic speech recognition (ASR) engine.
8 . The apparatus of claim 6 , wherein the call audio is received at the CAS in near real time, and the call text is received at the CAS near real time.
9 . The apparatus of claim 6 , wherein the emotion comprises at least one of happy, anger, frustration, sad or neutral,
wherein the sentiment comprises at least one of positive, strongly positive, mildly positive, negative, strongly negative, mildly negative, or neutral, and
wherein the behaviour comprises at least one of polite, impolite, friendly, rude, empathetic and neutral,
wherein the determining the behavior comprises identifying a pair comprising the emotion and the sentiment, and optionally, rate of speech, speaker energy and excitement state of the speaker.
10 . The apparatus of claim 9 , wherein the method further comprises recommending a behavior for a second speaker in the audio, in response to the determined behavior of the first speaker.