Does Script Design Matter? Phonetic Transparency and CTC Decoding for N'Ko
This controlled-comparison paper asks whether script design changes CTC decoding behavior. The point is not that one script is culturally preferable, but that phonetic transparency can change what a recognizer can align and learn.
Paper workspace
Live draft structure
Artifacts
Final split-paper render
Final split-paper artifact for phonemic evaluation and script-aware measurement.
Open artifactEditable source
Draft PDF exists. The comparison framing should stay editable as the flagship paper evolves.
Source anchors
nko-brain-scanner/paper/current/paper4_script_advantage.tex
nko-brain-scanner/paper/final/02-phonemic-evaluation/paper.tex
Method tags
Ingest intersections
Status
Drafted.
Key claims
01
Orthographic design affects the learning problem faced by a decoder.
02
Phonetic transparency can make some error classes more interpretable.
03
Script-aware evaluation should be part of low-resource ASR methodology.
Public reading note
Drafted.
Standard skeleton
What this paper must keep proving
problem
A metric can change meaning when the writing system changes what each symbol carries.
method
Compare decoding behavior under script representations with different phonetic transparency.
implementation
CTC heads, controlled script targets, shared audio conditions, error-class analysis.
data
Matched speech/text examples where script representation can be varied without changing the acoustic input.
evaluation
CER plus interpretable error decomposition, not only aggregate score.
references
CTC alignment, orthographic depth, phoneme-grapheme mapping, low-resource evaluation.
openQuestions
How to isolate script transparency from data availability and tokenizer prior effects.
Checkpoints and references
Proof chain
Claim checkpoint
central-claim slot
Every central claim must point to a proof anchor or remain labeled as speculative.
Implementation checkpoint
implementation-map slot
Every method should identify the code path, harness, schema, or protocol that embodies it.
Evidence checkpoint
evidence-manifest slot
Every reported result should point to run IDs, packet IDs, data snapshots, commits, or review artifacts.
Reference checkpoint
references slot
Every external claim should resolve to a cited paper, benchmark, standard, or documented prior system.
Release checkpoint
release-gate slot
Every PDF needs a named condition before it can move from draft to citation-ready.