Gender domain adaptation for automatic speech recognition task
This work addresses speaker adaptation challenges in ASR for gender-specific applications, but it is incremental as it builds on existing fine-tuning techniques without major breakthroughs.
The paper tackled gender-specific adaptation for automatic speech recognition by fine-tuning Transformer models on gender subsets, achieving up to 5% lower word error rate on male subsets and 3% on female subsets, with models trained on gender subsets showing 1-2% higher accuracy compared to those tuned on the full dataset.
This paper is focused on the finetuning of acoustic models for speaker adaptation goals on a given gender. We pretrained the Transformer baseline model on Librispeech-960 and conduct experiments with finetuning on the gender-specific test subsets and. In general, we do not obtain essential WER reduction by finetuning techniques by this approach. We achieved up to ~5% lower word error rate on the male subset and 3% on the female subset if the layers in the encoder and decoder are not frozen, but the tuning is started from the last checkpoints. Moreover, we adapted our base model on the full L2 Arctic dataset of accented speech and fine-tuned it for particular speakers and male and female genders separately. The models trained on the gender subsets obtained 1-2% higher accuracy when compared to the model tuned on the whole L2 Arctic dataset. Finally, we tested the concatenation of the pretrained x-vector voice embeddings and embeddings from a conventional encoder, but its gain in accuracy is not significant.