改进语音助手的连续对话识别，减少说话开始时的错误。
Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents
- 保留跨语句上下文，避免每次重置状态
- 在对话起始处实现15%-21%的识别错误降低
- 适合需要连续对话理解的语音助手系统
现代语音助手系统依赖流式语音识别模型，在严格延迟约束下运行。本研究发现，由于实时处理中的内存限制，长停顿和回应对话现象会显著影响系统性能。尽管许多智能体流水线通过每轮重置状态来缓解问题，但这会丢弃重要上下文，导致回合起始时性能下降。本文提出两种状态管理策略，以保留跨语句上下文，减少起始错误。在两个先进流式模型和两个口语对话基准上的实验表明，最佳方法在语句起始处平均实现15%-21%的相对词错误率（WER）降低。
原文摘要 · Abstract (English)
Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While many agentic pipelines mitigate this by resetting state at each turn, this approach discards vital context and impairs performance at turn onsets. We propose two state-management strategies that preserve cross-utterance context to reduce onset errors. In experiments with two state-of-the-art streaming models on two spoken dialogue benchmarks, our best method yields an average of 15-21% relative WER reduction at utterance onsets.
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。