In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming ASR architecture that outputs a confusion network while maintaining limited latency, as needed for interactive applications. We show that 1-best results of our model are on par with a comparable RNN-T system, while the richer hypothesis set allows second-pass rescoring to achieve 10-20\% lower word error rate on the LibriSpeech task. We also show that our model outperforms a strong RNN-T baseline on a far-field voice assistant task.
@article{arxiv.2306.03778,
title = {Streaming Speech-to-Confusion Network Speech Recognition},
author = {Denis Filimonov and Prabhat Pandey and Ariya Rastrow and Ankur Gandhe and Andreas Stolcke},
journal= {arXiv preprint arXiv:2306.03778},
year = {2024}
}