用真实通话数据微调大模型，让客服语音识别更准更快。
Domain-Adaptive ASR for Telephony AI Agents: Fine-tuning Canary Flash Models for Enterprise Contact Center Applications
- 用真实通话录音构建数据集，针对性增强电话音频识别能力。
- 噪声环境下字符错误率从23.31%降至9.04%，关键术语准确率提升至96.22%。
- 适合企业级语音机器人部署，兼顾高精度与实时响应。
本文介绍Botnoi团队使用NVIDIA NeMo框架，快速微调开源NVIDIA Canary 180M Flash与1B Flash多任务模型，用于语音转文字任务，重点针对电话音质音频。为支持这一适配，我们基于真实语音机器人系统录音和提示语音，构建了面向电话场景的微调数据集，并引入电话特化增强技术。通过四项实验评估：语言适配（泰语）、电话鲁棒性、领域专有术语（姓名与地址）及延迟，采用字符错误率（CER）衡量准确性，实时因子（RTFx）衡量推理速度。结果表明，微调显著提升噪声环境下的识别性能，在BOTNOI电话数据上将CER从23.31%降至9.04%；通过领域特化适配，关键业务术语（姓名与地址）的CER从16.98%降至3.78%。整体结果表明，领域自适应微调可在保持实时响应能力的前提下，有效提升业务关键术语的识别精度，适用于生产环境语音机器人部署。
原文摘要 · Abstract (English)
This technical report describes Botnoi Group's methodology and results for rapidly fine-tuning the open-source NVIDIA Canary 180M Flash and NVIDIA Canary 1B Flash multitask models for speech-to-text tasks using the NVIDIA NeMo framework, with a focus on telephony-grade audio. To support this adaptation, we construct a telephony-oriented fine-tuning dataset from live voicebot system recordings and prompted speech with telephony-oriented augmentation. We evaluate four targeted experiments-language adaptation (Thai), telephony robustness, domain-specific jargon (names and addresses), and latency-using character error rate (CER) for accuracy and real-time factor (RTFx) for inference speed. Results show that fine-tuning substantially improves recognition in noisy telephony environments, reducing CER from 23.31% to 9.04% on BOTNOI telephony data, and further improves business-critical names and addresses from 16.98% to 3.78% CER through domain-specific adaptation. Overall, our results show that domain-adaptive fine-tuning enhances business-critical terminology while preserving real-time responsiveness for production voicebot deployments.
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。