Speech data from different domains has distinct acoustic and linguistic characteristics. It is common to train a single multidomain model such as a Conformer transducer for speech recognition on a mixture of data from all domains. However, changing data in one domain or adding a new domain would require the multidomain model to be retrained. To this end, we propose a framework called modular domain adaptation (MDA) that enables a single model to process multidomain data while keeping all parameters domain-specific, i.e., each parameter is only trained by data from one domain. On a streaming Conformer transducer trained only on video caption data, experimental results show that an MDA-based model can reach similar performance as the multidomain model on other domains such as voice search and dictation by adding per-domain adapters and per-domain feed-forward networks in the Conformer encoder.
@article{arxiv.2305.13408,
title = {Modular Domain Adaptation for Conformer-Based Streaming ASR},
author = {Qiujia Li and Bo Li and Dongseong Hwang and Tara N. Sainath and Pedro M. Mengibar},
journal= {arXiv preprint arXiv:2305.13408},
year = {2023}
}