Fotheidil: an Automatic Transcription System for the Irish Language

TL;DR

Fotheidil is the first web-based Irish language transcription system utilizing speech AI technologies, semi-supervised learning, and sequence-to-sequence models, with ongoing community-driven improvements and public availability.

Contribution

It introduces a novel Irish-specific ASR system with semi-supervised training and a new sequence-to-sequence approach for punctuation and capitalization restoration.

Findings

Substantial improvements in out-of-domain and dialect recognition.

Effective semi-supervised learning enhances acoustic model performance.

Sequence-to-sequence models outperform traditional classification methods.

Abstract

This paper sets out the first web-based transcription system for the Irish language - Fotheidil, a system that utilises speech-related AI technologies as part of the ABAIR initiative. The system includes both off-the-shelf pre-trained voice activity detection and speaker diarisation models and models trained specifically for Irish automatic speech recognition and capitalisation and punctuation restoration. Semi-supervised learning is explored to improve the acoustic model of a modular TDNN-HMM ASR system, yielding substantial improvements for out-of-domain test sets and dialects that are underrepresented in the supervised training set. A novel approach to capitalisation and punctuation restoration involving sequence-to-sequence models is compared with the conventional approach using a classification model. Experimental results show here also substantial improvements in performance. The system will be made freely available for public use, and represents an important resource to researchers and others who transcribe Irish language materials. Human-corrected transcriptions will be collected and included in the training dataset as the system is used, which should lead to incremental improvements to the ASR model in a cyclical, community-driven fashion.