Description
Subtract nonSpeechTokens from totalTokens for eligibleTokens and overlappingUnintelligible from unintelligibleTokens for eligibleUnintelligible, then divide.
Speech and language research can use periods, samples, utterances, phoneme tokens, transcript labels, and timed observations. Counts and durations give different denominators, while missing or unscorable records need an explicit policy. Arithmetic on these annotations does not itself establish a validated clinical measure.
Subtract nonSpeechTokens from totalTokens for eligibleTokens and overlappingUnintelligible from unintelligibleTokens for eligibleUnintelligible, then divide.
When to use this tool
Use Speech Transcript Unintelligible Span Share when you need the stated acoustic, annotation, timing, or record-support calculation for supplied research data.
How to use the tool and how it works
- Enter totalTokens, unintelligibleTokens, nonSpeechTokens, overlappingUnintelligible. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read eligibleTokens, eligibleUnintelligible, share. Use the output convention below.
Subtract nonSpeechTokens from totalTokens for eligibleTokens and overlappingUnintelligible from unintelligibleTokens for eligibleUnintelligible, then divide. Require feasible nonnegative integer categories and positive eligible base.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| totalTokens | Total Tokens | Required. Safe integer; minimum 1. |
| unintelligibleTokens | Unintelligible Tokens | Required. Safe integer; minimum 0. |
| nonSpeechTokens | Non Speech Tokens | Required. Safe integer; minimum 0. |
| overlappingUnintelligible | Count included in both non-speech and unintelligible groups. | Required. Safe integer; minimum 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| eligibleTokens | Eligible Tokens | Required. Safe integer. |
| eligibleUnintelligible | Eligible Unintelligible | Required. Safe integer. |
| share | Dimensionless fraction using the stated denominator; not a percentage numeral. | Required. Finite number. |
{
"input": {
"totalTokens": 100,
"unintelligibleTokens": 20,
"nonSpeechTokens": 10,
"overlappingUnintelligible": 5
},
"output": {
"eligibleTokens": 90,
"eligibleUnintelligible": 15,
"share": 0.16666666666666666
}
}Limitations and assumptions
- Overlap is supplied to avoid counting non-speech tokens as unintelligible speech. Token definitions and transcript annotations are not validated or converted into a clinical intelligibility score.
- The field tables state structural bounds; the mechanics also specify cross-field constraints. Malformed inputs and unsupported domains cause errors. A successful false flag, empty branch value, or zero placeholder has the meaning stated above and is distinct from an input error.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Signed zero is exported as zero.
Alternative or Complementary methods
Use validated acoustic extraction and annotation procedures for the intended research task. A clinical interpretation needs an appropriate assessment method beyond this supplied-data calculation.
References
Similar or alternative tools
- Speech Fluency Research Event Denominator
Compute a supplied event rate under an explicit word or syllable denominator.
- Speech Sample Coder Agreement One Token
Compare supplied coder tokens after pairwise missing-token exclusion.