ManWav: The First Manchu ASR Model
It addresses the problem of technology access for marginalized linguistic communities, though it is incremental as it applies an existing method to new data.
This study tackled the lack of Automatic Speech Recognition (ASR) for the critically endangered Manchu language by introducing the first Manchu ASR model, ManWav, which reduced character error rate by 0.02 and word error rate by 0.13 using augmented data.
This study addresses the widening gap in Automatic Speech Recognition (ASR) research between high resource and extremely low resource languages, with a particular focus on Manchu, a critically endangered language. Manchu exemplifies the challenges faced by marginalized linguistic communities in accessing state-of-the-art technologies. In a pioneering effort, we introduce the first-ever Manchu ASR model ManWav, leveraging Wav2Vec2-XLSR-53. The results of the first Manchu ASR is promising, especially when trained with our augmented data. Wav2Vec2-XLSR-53 fine-tuned with augmented data demonstrates a 0.02 drop in CER and 0.13 drop in WER compared to the same base model fine-tuned with original data.