论文标题
部分可观测时空混沌系统的无模型预测
Filter-based Discriminative Autoencoders for Children Speech Recognition
论文作者
论文摘要
儿童言语认可是必不可少的，但由于儿童言语的多样性而具有挑战性。在本文中，我们提出了一种基于过滤器的判别自动编码器，用于声学建模。为了滤除各种扬声器类型和音高的影响，扬声器和音高特征的辅助信息与声音特征一起输入了编码器，以生成语音嵌入。在训练阶段，解码器使用编码器提取的辅助信息和语音嵌入来重建输入声学特征。通过同时减少ASR损失和功能重建误差来训练自动编码器。该框架可以使语音嵌入更纯净，从而导致更准确的Senone（Triphone-STATE）得分。与基线系统相比，我们的系统在CMU Kids语料库的测试集进行了评估，相对降低了7.8％。在域的适应实验中，我们的系统还表现出英国重值PF-Star任务的基线系统。
Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various speaker types and pitches, auxiliary information of the speaker and pitch features is input into the encoder together with the acoustic features to generate phonetic embeddings. In the training phase, the decoder uses the auxiliary information and the phonetic embedding extracted by the encoder to reconstruct the input acoustic features. The autoencoder is trained by simultaneously minimizing the ASR loss and feature reconstruction error. The framework can make the phonetic embedding purer, resulting in more accurate senone (triphone-state) scores. Evaluated on the test set of the CMU Kids corpus, our system achieves a 7.8% relative WER reduction compared to the baseline system. In the domain adaptation experiment, our system also outperforms the baseline system on the British-accent PF-STAR task.
