Register vs Contour Tone Classifier
Screen observed relative pitch trajectory under explicit tolerance for flat versus rising/falling/turning contour, preserving complex/subthreshold evidence; not a language’s tone-system classification or fundamental-frequency extraction.
Description
A sampled relative-pitch trajectory can be flat, directional or turning.
A sampled relative-pitch trajectory can be flat, directional or turning. A declared tolerance controls which adjacent changes count as trends.1
Enter at least two pitch levels0–10 and tolerance 0–10. Classify inclusive flat excursion first; then significant-sign sequences distinguish rise/fall, one turn or complex/subthreshold contour. Return excursion, final−initial and switch count.
When to use Register vs Contour Tone Classifier
Use Register vs Contour Tone Classifier when you need to evaluate the supplied records under the calculation and evidence rules below. No fundamental frequency extraction or language tone-system classification is performed.
Prepare explicit text tokens, annotated language observations, caller mappings or a supported locale as requested. Preserve source evidence and the stated Unicode counting convention.
How to use Register vs Contour Tone Classifier and understand its results
- Prepare explicit text tokens, annotated language observations, caller mappings or a supported locale as requested. Preserve source evidence and the stated Unicode counting convention.
- Enter relativePitchSamples, callerFlatExcursionTolerance using the field table and calculation rules, then run the tool.
- Read observedToneShape, observedPitchExcursion, signedFinalMinusInitialPitch, significantTrendSwitchCount. The explanation below defines the units, signs, ordering and any flags or placeholder values.
- If the tool reports an input issue, correct the values and run it again. Apply the stated assumptions when interpreting a successfully returned result.
| Input field | Meaning | Value type; see rules below | Requirement |
|---|---|---|---|
| relativePitchSamples | Relative pitch samples | list of number | Required |
| callerFlatExcursionTolerance | Caller flat excursion tolerance | number | Required |
Enter at least two pitch levels0–10 and tolerance 0–10. Classify inclusive flat excursion first; then significant-sign sequences distinguish rise/fall, one turn or complex/subthreshold contour. Return excursion, final−initial and switch count.
excursion=max−min; significant changes have absolute delta>tolerance Units, indexing, boundary conditions and exceptional cases are defined in the calculation rules above.
| Output field | Meaning | Value type |
|---|---|---|
| observedToneShape | Observed tone shape | string |
| observedPitchExcursion | Observed pitch excursion | number |
| signedFinalMinusInitialPitch | Signed final minus initial pitch | number |
| significantTrendSwitchCount | Significant trend switch count | number |
{
"input": {
"relativePitchSamples": [
2,
2,
2
],
"callerFlatExcursionTolerance": 0
},
"output": {
"observedToneShape": "register-flat",
"observedPitchExcursion": 0,
"signedFinalMinusInitialPitch": 0,
"significantTrendSwitchCount": 0
}
}Limitations and assumptions
No fundamental frequency extraction or language tone-system classification is performed.
Numeric inputs, where present, must be finite. Follow the calculation-specific rules for overflow, underflow and exceptional cases. Numeric lists are limited to 10,000 entries; string lists to 128 strings of at most 128 characters each. The rules above may impose smaller limits. Missing required fields, extra fields, wrong value types and violations of the calculation rules are input errors.
Alternative or Complementary methods
Use Stress-Timed vs Syllable-Timed Classifier: Rhythm metrics summarize measured interval variability. They do not by themselves establish stress timing, syllable timing or isochrony. For a complementary task, use Syllable Structure Type Lookup (CV/CVC): A syllable pattern records onset, nucleus and coda under a caller’s segmentation. Multiple V symbols may represent a multi-vowel nucleus.
References
-
Register vs Contour Tone Classifier — tool.io
Similar or alternative tools
- Stress-Timed vs Syllable-Timed Classifier
Rhythm metrics summarize measured interval variability. They do not by themselves establish stress timing, syllable timing or isochrony.
- Syllable Structure Type Lookup (CV/CVC)
A syllable pattern records onset, nucleus and coda under a caller’s segmentation. Multiple V symbols may represent a multi-vowel nucleus.