基于CTC和分段CRF的语音识别多任务学习
Multitask Learning with CTC and Segmental CRF for Speech Recognition
摘要：
分段条件随机场（SCRFs）和连接主义时间分类（CTC）是两种用于语音识别模型端到端训练的序列标记方法。这两个模型定义了一个转录概率边缘化的决定潜在的分割替代品，以获得一个序列概率：前者使用一个全球标准化的联合模型的段标签和持续时间，后者分类每个帧作为输出符号或“延续”的前一个标签。在本文中，我们训练识别模型，通过优化SCRF和CTC损失之间的插值，其中相同的递归神经网络（RNN）编码器用于两个输出的特征提取。我们发现，这个多任务目标提高识别精度时，无论是SCRF或CTC模型解码。此外，我们还证明了CTC也可以用于预训练RNN编码器，这提高了学习联合模型时的收敛速度。
英文摘要：
Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by marginalizing decisions about latent segmentation alternatives to derive a sequence probability: the former uses a globally normalized joint model of segment labels and durations, and the latter classifies each frame as either an output symbol or a "continuation" of the previous label. In this paper, we train a recognition model by optimizing an interpolation between the SCRF and CTC losses, where the same recurrent neural network (RNN) encoder is used for feature extraction for both outputs. We find that this multitask objective improves recognition accuracy when decoding with either the SCRF or CTC models. Additionally, we show that CTC can also be used to pretrain the RNN encoder, which improves the convergence rate when learning the joint model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
