In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for offline recognition of voice search queries, with up to 2B model parameters. The encoders of our models use the neural architecture of Google's universal speech model (USM), with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. We perform extensive studies on vocabulary size, time reduction strategy, and its generalization performance on long-form test sets. Despite the speculation that, as the model size increases, CTC can be as good as RNN-T which builds label dependency into the prediction, we observe that a 900M RNN-T clearly outperforms a 1.8B CTC and is more tolerant to severe time reduction, although the WER gap can be largely removed by LM shallow fusion.

翻译：本研究探索了两种主流的端到端自动语音识别（ASR）模型，即连接主义时序分类（CTC）和RNN-Transducer（RNN-T），用于离线识别语音搜索查询，模型参数规模高达20亿。模型编码器采用谷歌通用语音模型（USM）的神经架构，并附加漏斗池化层以显著降低帧率，从而加速训练与推理。我们针对词汇量规模、时间压缩策略及其在长语音测试集上的泛化性能开展了广泛研究。尽管存在猜想认为随着模型规模增大，CTC可与构建标签依赖性的RNN-T性能相当，但我们观察到9亿参数的RNN-T明显优于18亿参数的CTC，且对大幅时间压缩具有更强容忍性，尽管通过语言模型浅层融合可在很大程度上消除词错误率（WER）差距。