arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.06113cs.CL
收藏

基于说话人分类器的深度神经网络声学建模说话人自适应训练

Speaker Cluster-Based Speaker Adaptive Training for Deep Neural Network Acoustic Modeling

Sony Computer Entertainment America(索尼电脑娱乐美国公司)

Wei Chu, Ruxin Chen

摘要:

提出了一种基于深度神经网络-隐马尔可夫模型(DNN-HMM)的说话人自适应训练(SAT)方法。在训练期间,使用基于i向量的距离度量来对声学上彼此相邻的扬声器进行分层聚类。然后,针对每个扬声器集群自适应地训练具有扬声器相关层的DNN。在解码开始之前,通过比较基于i向量的距离,将测试集中的未见过的说话人匹配到最近的说话人聚类。匹配的说话人聚类的先前训练的DNN用于解码测试说话人的话语。所提出的方法在大词汇量自发语音识别任务上的性能在具有1500小时语音的训练集和具有1774个话语的24个说话者的测试集上进行评估。与具有11.6%的基线字出错率的说话人无关DNN相比,从所提出的方法观察到字出错率相对降低6.8%。

英文摘要:

A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are hierarchically clustered using an i-vector based distance metric. DNNs with speaker dependent layers are then adaptively trained for each cluster of speakers. Before decoding starts, an unseen speaker in test set is matched to the closest speaker cluster through comparing i-vector based distances. The previously trained DNN of the matched speaker cluster is used for decoding utterances of the test speaker. The performance of the proposed method on a large vocabulary spontaneous speech recognition task is evaluated on a training set of with 1500 hours of speech, and a test set of 24 speakers with 1774 utterances. Comparing to a speaker independent DNN with a baseline word error rate of 11.6%, a relative 6.8% reduction in word error rate is observed from the proposed method.

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。

↑