改进语音识别模型训练，利用左右标签上下文提升小样本效果
Right Label Context in End-to-End Training of Time-Synchronous ASR Models
- 设计分因子损失函数，显式建模左右标签上下文
- 在300小时数据下词错误率降低1.8%，960小时数据下提升1.2%
- 适合低资源语音识别场景，尤其对小样本训练有显著帮助
当前时间同步序列到序列语音识别模型采用逐序列交叉熵训练，对所有对齐路径求和。由于其判别式框架，将正确标签上下文纳入训练目标梯度会导致归一化问题，数学上不严谨。经典混合神经网络隐马尔可夫模型（NN-HMM）虽具生成式框架，可条件化右侧标签上下文，但因状态绑定，其具体身份未显式建模。本文提出一种包含辅助左右标签上下文的分因子损失函数，对所有对齐路径求和。实验表明，该方法在数据有限时尤为有效。此外，我们还证明仅依赖全求和准则即可构建分因子混合HMM系统。测试基于Switchboard 300h与LibriSpeech 960h数据集。
原文摘要 · Abstract (English)
Current time-synchronous sequence-to-sequence automatic speech recognition (ASR) models are trained by using sequence level cross-entropy that sums over all alignments. Due to the discriminative formulation, incorporating the right label context into the training criterion's gradient causes normalization problems and is not mathematically well-defined. The classic hybrid neural network hidden Markov model (NN-HMM) with its inherent generative formulation enables conditioning on the right label context. However, due to the HMM state-tying the identity of the right label context is never modeled explicitly. In this work, we propose a factored loss with auxiliary left and right label contexts that sums over all alignments. We show that the inclusion of the right label context is particularly beneficial when training data resources are limited. Moreover, we also show that it is possible to build a factored hybrid HMM system by relying exclusively on the full-sum criterion. Experiments were conducted on Switchboard 300h and LibriSpeech 960h.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。