文本无关说话人识别中句级特征提取方法研究综述  

Utterance-level Feature Extraction in Text-independent Speaker Recognition:A Review

作　　者：陈晨[1,2] 韩纪庆[2] 陈德运[1] 何勇军[1] CHEN Chen;HAN Ji-Qing;CHEN De-Yun;HE Yong-Jun(Postdoctoral Research Station of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080;School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001)

机构地区：[1]哈尔滨理工大学计算机科学与技术博士后流动站,哈尔滨150080 [2]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001

出　　处：《自动化学报》2022年第3期664-688,共25页Acta Automatica Sinica

基　　金：国家自然科学基金(62101163);黑龙江省自然科学基金(LH2021F029);中国博士后科学基金(2021M701020);黑龙江省博士后专项经费(LBH-Z20020);黑龙江省普通高校基本科研业务费专项资金(2020-KYYWF-0341)资助。

摘　　要：句级(Utterance-level)特征提取是文本无关说话人识别领域中的重要研究方向之一.与只能刻画短时语音特性的帧级(Frame-level)特征相比,句级特征中包含了更丰富的说话人个性信息;且不同时长语音的句级特征均具有固定维度,更便于与大多数常用的模式识别方法相结合.近年来,句级特征提取的研究取得了很大的进展,鉴于其在说话人识别中的重要地位,本文对近期具有代表性的句级特征提取方法与技术进行整理与综述,并分别从前端处理、基于任务分段式与驱动式策略的特征提取方法,以及后端处理等方面进行论述,最后对未来的研究趋势展开探讨与分析.Utterance-level feature extraction is one of the most important researches in text-independent speaker recognition.Compared with the frame-level features which only contain the short-term speech characteristics,the utterance-level features can effectively capture more speaker discriminative information.Meanwhile,it also has another advantage that any utterance with a variable duration can be represented as a fixed-dimension feature.Thus,the utterance-level features are easy to integrate with most commonly-used pattern recognition methods.In recent years,the researches on utterance-level feature extraction have made great progress.Considering the importance of utterance-level feature extraction in speaker recognition,this paper will organize and summarize the typical methods.Specifically,the front-end processing,the feature extraction based on the task-segmented strategy and taskdriven strategy,and the back-end processing are introduced respectively.Finally,the future trends in speaker recognition are discussed and analyzed.

关 键 词：说话人识别 句级特征提取 任务分段式策略 任务驱动式策略 联合学习 

分 类 号：TN912.34[电子电信—通信与信息系统]