面向实用流式ASR的轻量级基于目标说话人的重叠语音转录
Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
AI总结：
提出一种轻量级基于目标说话人的流式ASR扩展方法，结合SI与SC模型及紧凑重叠检测器，在计算量仅增44%下将重叠语音WER从68.0%降至35.78%，实现高效可扩展的重叠转录。
摘要：
重叠语音仍是现实应用中自动语音识别（ASR）面临的主要挑战，尤其是在具有动态、多说话人交互的广播媒体中。我们提出了一种轻量级、基于目标说话人的扩展现有流式ASR系统的方法，以极小的计算开销实现重叠语音的实用转录。我们的方法结合了用于标准操作的说话人无关（SI）模型与在重叠场景中选择性应用的说话人条件（SC）模型。重叠检测通过在冻结的SI模型输出上训练的紧凑二分类器实现，以可忽略的成本提供准确分割。SC模型采用特征级线性调制（FiLM）融合说话人嵌入，并在合成混合数据上训练，以仅转录目标说话人。该方法支持动态说话人追踪，并以最小改动复用现有模块。在具有16%重叠率的捷克电视辩论测试集上评估，系统将重叠片段的WER从68.0%（基线）降至35.78%，同时总计算量仅增加44%。所提系统为连续ASR服务中的重叠转录提供了有效且可扩展的解决方案。
英文摘要：
Overlapping speech remains a major challenge for automatic speech recognition (ASR) in real-world applications, particularly in broadcast media with dynamic, multi-speaker interactions. We propose a light-weight, target-speaker-based extension to an existing streaming ASR system to enable practical transcription of overlapping speech with minimal computational overhead. Our approach combines a speaker-independent (SI) model for standard operation with a speaker-conditioned (SC) model selectively applied in overlapping scenarios. Overlap detection is achieved using a compact binary classifier trained on frozen SI model output, offering accurate segmentation at negligible cost. The SC model employs Feature-wise Linear Modulation (FiLM) to incorporate speaker embeddings and is trained on synthetically mixed data to transcribe only the target speaker. Our method supports dynamic speaker tracking and reuses existing modules with minimal modifications. Evaluated on a challenging set of Czech television debates with 16% overlap, the system reduced WER on overlapping segments from 68.0% (baseline) to 35.78% while increasing total computational load by only 44%. The proposed system offers an effective and scalable solution for overlap transcription in continuous ASR services.
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。
