融合语言与声学特征，提升电话访谈中的说话人分离效果
Language Modelling for Speaker Diarization in Telephonic Interviews
- 用LSTM网络结合字符级词嵌入和高斯混合模型声学得分进行迭代分类
- 在呼叫中心数据集上实现字级错误率降低84.29%（相比HMM/VB基线）
- 适合语音识别中需区分说话人的场景，尤其当语言信息更具区分性时
本文研究将语言与声学建模结合对说话人分离的增益。尽管传统系统仅依赖声学特征，但在某些场景下，语言数据包含更高区分度的说话人信息，甚至比声学特征更可靠。本研究分析了如何合理融合两类特征以获得良好效果。所提系统基于迭代算法，使用LSTM网络作为说话人分类器，输入为字符级词嵌入及前一轮迭代输出标签生成的基于GMM的声学得分。该算法在电话访谈音频组成的呼叫中心数据库上进行了评估。结果表明，声学特征与语言内容的结合使字级错误率（DER）相比HMM/VB基线系统降低84.29%。研究证实，语言信息可高效用于部分说话人识别任务。
原文摘要 · Abstract (English)
The aim of this paper is to investigate the benefit of combining both language and acoustic modelling for speaker diarization. Although conventional systems only use acoustic features, in some scenarios linguistic data contain high discriminative speaker information, even more reliable than the acoustic ones. In this study we analyze how an appropriate fusion of both kind of features is able to obtain good results in these cases. The proposed system is based on an iterative algorithm where a LSTM network is used as a speaker classifier. The network is fed with character-level word embeddings and a GMM based acoustic score created with the output labels from previous iterations. The presented algorithm has been evaluated in a Call-Center database, which is composed of telephone interview audios. The combination of acoustic features and linguistic content shows a 84.29% improvement in terms of a word-level DER as compared to a HMM/VB baseline system. The results of this study confirms that linguistic content can be efficiently used for some speaker recognition tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。