A Dual-Decoder Conformer for Multilingual Speech Recognition
This work addresses speech recognition for low-resource Indian languages, but it is incremental as it builds on existing transformer and multi-task learning methods.
The paper tackles low-resource multilingual speech recognition for Indian languages by proposing a dual-decoder Conformer model with auxiliary tasks, resulting in a significant reduction in word error rate (WER) compared to baseline and single-decoder approaches.
Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech recognition for Indian languages. Our proposed model consists of a Conformer [1] encoder, two parallel transformer decoders, and a language classifier. We use a phoneme decoder (PHN-DEC) for the phoneme recognition task and a grapheme decoder (GRP-DEC) to predict grapheme sequence along with language information. We consider phoneme recognition and language identification as auxiliary tasks in the multi-task learning framework. We jointly optimize the network for phoneme recognition, grapheme recognition, and language identification tasks with Joint CTC-Attention [2] training. Our experiments show that we can obtain a significant reduction in WER over the baseline approaches. We also show that our dual-decoder approach obtains significant improvement over the single decoder approach.