用非自回归模型修正说话人切分边界错误，提升语音对话识别准确率。
Speaker Tagging Correction With Non-Autoregressive Language Models
- 采用非自回归语言模型做第二轮纠错，聚焦跨说话人边界词的错误
- 在TAL和Fisher数据集上降低词级说话人错误率（WDER）
- 适合需要高精度说话人分离的会议记录、客服对话等场景
处理对话类语音应用不仅需识别语音内容，还需确定说话人身份。传统方法通过合并自动语音识别（ASR）与说话人聚类（SD）两个系统的输出完成任务。然而实际中，由于高时间分辨率的均匀分段、不准确的词时间戳、错误的聚类及说话人数估计、背景噪声等因素，说话人聚类性能常大幅下降。因此，自动检测并纠正错误至关重要。本文提出基于非自回归语言模型的第二轮说话人标签纠错系统，专门修正不同说话人句子交界处的词语误标问题。实验表明，该方法在TAL和Fisher测试集上均显著降低词级说话人错误率（WDER）。此外，在Post-ASR Speaker Tagging Correction挑战赛中，相较基线方法，本系统在跨说话人词错误率（cpWER）上取得明显提升。
原文摘要 · Abstract (English)
Speech applications dealing with conversations require not only recognizing the spoken words but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems, namely, an automatic speech recognition (ASR) system and a speaker diarization (SD) system. In practical settings, speaker diarization systems can experience significant degradation in performance due to a variety of factors, including uniform segmentation with a high temporal resolution, inaccurate word timestamps, incorrect clustering and estimation of speaker numbers, as well as background noise. Therefore, it is important to automatically detect errors and make corrections if possible. We used a second-pass speaker tagging correction system based on a non-autoregressive language model to correct mistakes in words placed at the borders of sentences spoken by different speakers. We first show that the employed error correction approach leads to reductions in word diarization error rate (WDER) on two datasets: TAL and test set of Fisher. Additionally, we evaluated our system in the Post-ASR Speaker Tagging Correction challenge and observed significant improvements in cpWER compared to baseline methods.
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。