Conversational Short-Phrase Speaker Diarization via Self-Adjusting Speech Segmentation and Embedding Extraction

IF 3.2 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Signal Processing Letters Pub Date : 2024-09-03 DOI:10.1109/LSP.2024.3453772

Haitian Lu;Gaofeng Cheng;Yonghong Yan

{"title":"Conversational Short-Phrase Speaker Diarization via Self-Adjusting Speech Segmentation and Embedding Extraction","authors":"Haitian Lu;Gaofeng Cheng;Yonghong Yan","doi":"10.1109/LSP.2024.3453772","DOIUrl":null,"url":null,"abstract":"Conversational short-phrase speaker diarization focuses on diarizing the phrases that are short in duration. Nonetheless, conventional speaker diarization systems fail to give enough importance to conversational short phrases. This letter proposed a novel speaker diarization system to address this issue. Firstly, we employ an RNN-T model for joint speech recognition and speaker change detection. The speech recognition results can be utilized directly in downstream tasks while the speaker change points serve as guidance for the following steps. Secondly, we introduce self-adjusting speech segmentation, which dynamically adjusts segment lengths based on the temporal distribution of speaker change points. Thirdly, we introduce self-adjusting embedding extraction, which employs speaker encoders trained under different speech duration conditions by projecting them to the same embedding space. Our method achieves a major reduction of Diarization Error Rate (DER) and Conversational Diarization Error Rate (CDER) on the MagicData-RAMC and Mixer 6 datasets.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Signal Processing Letters","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10663942/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Conversational short-phrase speaker diarization focuses on diarizing the phrases that are short in duration. Nonetheless, conventional speaker diarization systems fail to give enough importance to conversational short phrases. This letter proposed a novel speaker diarization system to address this issue. Firstly, we employ an RNN-T model for joint speech recognition and speaker change detection. The speech recognition results can be utilized directly in downstream tasks while the speaker change points serve as guidance for the following steps. Secondly, we introduce self-adjusting speech segmentation, which dynamically adjusts segment lengths based on the temporal distribution of speaker change points. Thirdly, we introduce self-adjusting embedding extraction, which employs speaker encoders trained under different speech duration conditions by projecting them to the same embedding space. Our method achieves a major reduction of Diarization Error Rate (DER) and Conversational Diarization Error Rate (CDER) on the MagicData-RAMC and Mixer 6 datasets.

查看原文本刊更多论文

通过自调整语音分割和嵌入式提取实现对话短语说话者日记化

会话短语说话者日记法侧重于记录持续时间较短的短语。然而，传统的说话者日记系统未能对会话短语给予足够的重视。针对这一问题，本文提出了一种新型的说话者日记系统。首先，我们采用 RNN-T 模型进行联合语音识别和说话人变化检测。语音识别结果可直接用于下游任务，而说话人变化点则可为后续步骤提供指导。其次，我们引入了自调整语音分割技术，根据说话人变化点的时间分布动态调整分割长度。第三，我们引入了自调整嵌入提取，通过将在不同语音时长条件下训练的扬声器编码器投射到相同的嵌入空间，从而使用扬声器编码器。在 MagicData-RAMC 和 Mixer 6 数据集上，我们的方法大大降低了 Diarization Error Rate (DER) 和 Conversational Diarization Error Rate (CDER)。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Signal Processing Letters 工程技术-工程：电子与电气

CiteScore

7.40

自引率

12.80%

发文量

339

审稿时长

2.8 months

期刊介绍： The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing. Papers published in the Letters can be presented within one year of their appearance in signal processing conferences such as ICASSP, GlobalSIP and ICIP, and also in several workshop organized by the Signal Processing Society.