Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation model, inverse text normalization) into one single model. This greatly simplifies training and inference and hence makes RNN-T a desirable choice for ASR systems. In this work, we investigate use of RNN-T in applications that require a tune-able latency budget during inference time. We also improved the decoding speed of the originally proposed RNN-T beam search algorithm. We evaluated our proposed system on English videos ASR dataset and show that neural RNN-T models can achieve comparable WER and better computational efficiency compared to a well tuned hybrid ASR baseline.

中文翻译：

---

RNN-T 用于延迟控制的 ASR，具有改进的波束搜索

基于神经换能器的系统，例如用于自动语音识别 (ASR) 的 RNN 换能器 (RNN-T)，将传统混合 ASR 系统的各个组件（声学模型、语言模型、标点符号模型、逆向文本归一化）融合到一个模型中。这极大地简化了训练和推理，因此使 RNN-T 成为 ASR 系统的理想选择。在这项工作中，我们研究了 RNN-T 在推理时间内需要可调整延迟预算的应用程序中的使用。我们还提高了最初提出的 RNN-T 波束搜索算法的解码速度。我们在英语视频 ASR 数据集上评估了我们提出的系统，并表明与经过良好调整的混合 ASR 基线相比，神经 RNN-T 模型可以实现可比的 WER 和更好的计算效率。