Low-resource speech recognition and dialect identification of Irish in a multi-task framework
About
This paper explores the use of Hybrid CTC/Attention encoder-decoder models trained with Intermediate CTC (InterCTC) for Irish (Gaelic) low-resource speech recognition (ASR) and dialect identification (DID). Results are compared to the current best performing models trained for ASR (TDNN-HMM) and DID (ECAPA-TDNN). An optimal InterCTC setting is initially established using a Conformer encoder. This setting is then used to train a model with an E-branchformer encoder and the performance of both architectures are compared. A multi-task fine-tuning approach is adopted for language model (LM) shallow fusion. The experiments yielded an improvement in DID accuracy of 10.8% relative to a baseline ECAPA-TDNN, and WER performance approaching the TDNN-HMM model. This multi-task approach emerges as a promising strategy for Irish low-resource ASR and DID.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Automatic Speech Recognition | Indian Languages ASR dataset 8 dialects: bh, bn, ch, kn, mg, mr, mt, te | CER (bh)4.91 | 8 | |
| Dialect Identification | RESPIN (test) | BH75.72 | 7 |