Building competitive hybrid hidden Markov model~(HMM) systems for automatic speech recognition~(ASR) requires a complex multi-stage pipeline consisting of several training criteria. The recent sequence-to-sequence models offer the advantage of having simpler pipelines that can start from-scratch. We propose a purely neural based single-stage from-scratch pipeline for a context-dependent hybrid HMM that offers similar simplicity. We use an alignment from a full-sum trained zero-order posterior HMM with a BLSTM encoder. We show that with this alignment we can build a Conformer factored hybrid that performs even better than both a state-of-the-art classic hybrid and a factored hybrid trained with alignments taken from more complex Gaussian mixture based systems. Our finding is confirmed on Switchboard 300h and LibriSpeech 960h tasks with comparable results to other approaches in the literature, and by additionally relying on a responsible choice of available computational resources.

翻译：构建用于自动语音识别(ASR)的竞争性混合隐马尔可夫模型(HMM)系统需要复杂的多阶段流水线，包含多个训练准则。近年来的序列到序列模型具有更简单流水线的优势，可以从零开始训练。我们提出了一种纯神经网络的单阶段从零开始流水线，用于上下文相关的混合HMM，具有类似的简洁性。我们采用基于全和训练、结合BLSTM编码器的零阶后验HMM生成的声学对齐。实验表明，利用此对齐，我们能够构建一个Conformer因子化混合模型，其性能不仅超越了最先进的经典混合模型，还优于采用基于更复杂高斯混合系统生成的声学对齐训练的因子化混合模型。该发现在Switchboard 300h和LibriSpeech 960h任务上得到了验证，结果与文献中其他方法相当，同时得益于对可用计算资源的合理选择。