A 33M-parameter raw-audio CTC model with 19-block RoPE E-Branchformer achieves 9.19% whitespace-insensitive IPA CER on a 16,660-utterance 41-language test set, outperforming a 575M-parameter PhoneticXEUS baseline at 9.78% under matched normalization.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encoder
A 33M-parameter raw-audio CTC model with 19-block RoPE E-Branchformer achieves 9.19% whitespace-insensitive IPA CER on a 16,660-utterance 41-language test set, outperforming a 575M-parameter PhoneticXEUS baseline at 9.78% under matched normalization.