Graph Temporal Classification trained on multiple G2P pronunciations per word reduces phoneme error rates versus CTC with one pronunciation: English 32.9 to 28.8, Dutch 23.9 to 23.0.
The nature of phonetic transcription,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Graph Connectionist Temporal Classification for Phoneme Recognition
Graph Temporal Classification trained on multiple G2P pronunciations per word reduces phoneme error rates versus CTC with one pronunciation: English 32.9 to 28.8, Dutch 23.9 to 23.0.