Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
复制标题
DOI：
10.1109/ojsp.2020.3045349
复制
发表时间：
2020-08
影响因子：
2.8
通讯作者：
P. Bell;Joachim Fainberg;Ondrej Klejch;Jinyu Li;S. Renals;P. Swietojanski
中科院分区：
文献类型：
--
作者：
P. Bell;Joachim Fainberg;Ondrej Klejch;Jinyu Li;S. Renals;P. Swietojanski
我们提出了一个结构化的概述基于神经网络的语音识别的自适应算法，考虑混合隐马尔可夫模型/神经网络系统和端到端的神经网络系统，重点是说话人自适应，域自适应，和口音自适应。概述的特点自适应算法的基础上嵌入，模型参数自适应，或数据增强。我们提出了一个荟萃分析的语音识别自适应算法的性能，根据文献中报道的相对错误率降低。
We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.