面向电话智能体的领域自适应ASR：针对企业联络中心应用微调Canary Flash模型

中文摘要 AI 辅助

本技术报告阐述了Botnoi Group的方法与成果：基于NVIDIA NeMo框架，针对电话级音频快速微调开源NVIDIA Canary 180M Flash及NVIDIA Canary 1B Flash多任务模型以完成语音转文本任务。为支撑该适配，我们从实时语音机器人系统录音及经电话导向增强的提示语音中构建了电话导向微调数据集。我们开展四项针对性实验：语言适配（泰语）、电话鲁棒性、领域特定术语（姓名与地址）、延迟评估，采用字符错误率（CER）衡量准确率、实时因子（RTFx）衡量推理速度。结果显示，微调可显著提升嘈杂电话环境下的识别性能，在BOTNOI电话数据上将CER从23.31%降至9.04%；经领域特定适配，业务关键的姓名与地址的CER进一步从16.98%降至3.78%。总体而言，我们的结果表明，领域自适应微调可在保持生产级语音机器人部署实时响应性的同时，提升业务关键术语的识别效果。

英文摘要

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.

发表机构

• Botnoi Group（博特诺伊集团）

机构由 AI 辅助整理，请以论文原文为准。