Fangyuan Wang, Xiyuan Wang, Taocun Yang, Weizhong Tang, Bo Xu, & Bo Xu (2026). Swichformer: Switch context powered chunk-wise conformer for end-to-end streaming automatic speech recognition. Speech Communication. https://doi.org/10.1016/j.specom.2026.103490
Fangyuan Wang, et al. “Swichformer: Switch context powered chunk-wise conformer for end-to-end streaming automatic speech recognition.” Speech Communication, 2026. doi:10.1016/j.specom.2026.103490.
@article{Wang2026,
title = {Swichformer: Switch context powered chunk-wise conformer for end-to-end streaming automatic speech recognition},
author = {Wang, Fangyuan and Wang, Xiyuan and Yang, Taocun and Tang, Weizhong and Xu, Bo and Xu, Bo},
journal = {Speech Communication},
year = {2026},
doi = {10.1016/j.specom.2026.103490},
url = {https://doi.org/10.1016/j.specom.2026.103490}
}