arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1509.02409cs.LGcs.CLcs.SD
收藏

多领域语音识别的数据选择迁移学习

Data-selective Transfer Learning for Multi-Domain Speech Recognition

University of Sheffield(谢菲尔德大学)

Mortaza Doulaty, Oscar Saz, Thomas Hain

摘要:

自动语音识别声学模型训练中的负迁移已经在诸如域变化或说话人特征的几种情况下被报道。本文提出了一种新的技术,以克服负迁移的有效选择语音数据的声学模型训练。在这里,数据是根据与特定目标的相关性来选择的。基于似然比的子模函数用于确定每个训练话语与目标测试集在声学上的相似程度。该方法进行了评估,在一个广泛的领域的数据集,包括从广播和电视广播,电话交谈,会议,讲座和阅读讲话的讲话。实验表明,该技术既发现相关数据,并限制负迁移。6小时测试集的结果显示,与使用基于PLP的模型中的所有数据相比,使用数据选择的相对改进为4%,使用DNN功能的相对改进为2%。

英文摘要:

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by efficient selection of speech data for acoustic model training. Here data is chosen on relevance for a specific target. A submodular function based on likelihood ratios is used to determine how acoustically similar each training utterance is to a target test set. The approach is evaluated on a wide-domain data set, covering speech from radio and TV broadcasts, telephone conversations, meetings, lectures and read speech. Experiments demonstrate that the proposed technique both finds relevant data and limits negative transfer. Results on a 6--hour test set show a relative improvement of 4% with data selection over using all data in PLP based models, and 2% with DNN features.

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。

↑