In our previous work we demonstrated that a single headed attention
encoder-decoder model is able to reach state-of-the-art results in
conversational speech recognition. In this paper, we further improve the
results for both Switchboard 300 and 2000. Through use of an improved
optimizer, speaker vector embeddings, and alternative speech representations we
reduce the recognition errors of our LSTM system on Switchboard-300 by 4%
relative. Compensation of the decoder model with the probability ratio approach
allows more efficient integration of an external language model, and we report
5.9% and 11.5% WER on the SWB and CHM parts of Hub5'00 with very simple LSTM
models. Our study also considers the recently proposed conformer, and more
advanced self-attention based language models. Overall, the conformer shows
similar performance to the LSTM; nevertheless, their combination and decoding
with an improved LM reaches a new record on Switchboard-300, 5.0% and 10.0% WER
on SWB and CHM. Our findings are also confirmed on Switchboard-2000, and a new
state of the art is reported, practically reaching the limit of the benchmark.

本论文通过改进优化器、使用说话者向量嵌入和替代的语音表示，以及采用概率比率方法补偿解码模型，成功降低了 LSTM 系统在 Switchboard-300 上相对识别误差 4%，并在 Hub5'00 的 SWB 和 CHM 部分报告了 5.9% 和 11.5% 的字误率，并在 Switchboard-300 上实现了新的最佳结果，同时探讨了 conformer 和更先进的自注意力语言模型及其对现有性能的贡献。