V-Blaze and V-Cloud Online Help (May 2020)

Emotion, Sentiment, and Gender

Table 1. Emotion, Sentiment, and Gender

Name

Values

Description

emotion

false (default), true

If set to true, Voci’s emotion detection feature uses a synthesis of acoustic features and word sentiment scores to determine if a given utterance is Strongly Positive, Positive, Neutral, Negative, or Strongly Negative.

Emotion detection is a licensed optional feature.

gender

false (default), true

Set gender=true to activate gender detection. For each utterance, Voci will attempt to determine if the speaker is male or female.

Gender Identification is a licensed optional feature.

rawemotion

true, false

If set to "true", includes "emotion only" information in the results. Possible return values are NONANGRY and ANGRY. If an utterance is too short for emotion detection, this tag will be set to "null." This parameter is useful for debugging and tuning and should not be used in the production flow.

raw_events

true, false

Includes an additional "raw_events" list in the JSON output under utterances. This includes silence, filler words, wordex, and un-punctuated text. This parameter is useful for debugging and tuning and should not be used in the production flow.

This parameter does not process any substations.

senti_list

filename , filename2...

The name(s) of the sentiment list(s) to be applied during transcription.

senti_rules

Specifies a newline-escaped string that contains the sentiment rules to use. This option enables you to augment the default sentiment rules that are used. Rules specified with the senti_rules tag are applied after any rules in the files identified by the senti_list tag. See senti_rules for additional information.