Skip to main content

Word Tagging

Transcription:BatchReal-TimeDeployments:All

Speechmatics outputs in the transcript a metadata tag to indicate whether a word is a profanity or a disfluency.

You can also request the automatic removal of disfluencies from the transcript.

Profanity Tagging​

You can use this tag in order to identify, redact, or obfuscate profanities and integrate this data into your own workflows.

Profanity tagging is available for the following languages:

  • English (EN)
  • Italian (IT)
  • Spanish (ES)

Note that the list of profanities in each language is not alterable.

An example of how this looks is below.

"results": [
  {
    "alternatives": [
      {
        "confidence": 1.0,
        "content": "$PROFANITY",
        "language": "en",
        "speaker": "UU",
        "tags": [
          "profanity"
        ]
      }
    ],
    "end_time": 18.03,
    "start_time": 17.61,
    "type": "word"
  }
]

Disfluency Tagging​

A disfluency here refers to a set list of words that imply hesitation or indecision, and is available in English language only. Please note that while disfluency can cover a range of items like stuttering and interjections, here it is only used to tag words such as 'hmm' or 'um'. The full list of words tagged as disfluencies is as follows:

huh
aha
ah
aw
eh
err
hmm
mm
um
uh
uh-oh
uh-huh
uh-uh
mhm
a-ha
aah
aahh
aaw
ah-ha
ahaa
ahh
ahha
aww
eeh
erm
hhm
hhmm
hm
huh-uh
m-hm
uggh
ugh
ughh
uhh
uhhm
uhm
uhmm
umm
uuh
uuhh
uum

An example of a word tagged as disfluency is below:

"results": [
  {
    "alternatives": [
      {
        "confidence": 1.0,
        "content": "hmm",
        "language": "en",
        "speaker": "UU",
        "tags": [
          "disfluency"
        ]
      }
    ],
    "end_time": 18.03,
    "start_time": 17.61,
    "type": "word"
  }
]

Disfluency Removal​

Transcription:BatchReal-TimeDeployments:On-Prem ContainersSaaS

Disfluencies can be automatically removed from your transcript. You can turn this option on through the transcript_filtering_config settings. The default value of remove_disfluencies is false, and setting it to true turns on disfluency removal.

"transcription_config": {
    "language": "en",
    "transcript_filtering_config": {
        "remove_disfluencies": true
    }
}

When disfluencies are removed, they do not show up in the transcript output at all. An example of output with and without disfluency removal would look something like the following:

Without disfluency removal:

I, uh, want a sandwich. Um, what would you like?

With disfluency removal:

I want a sandwich. What would you like?