arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01931cs.LGcs.CLcs.SDeess.AS
收藏

数字微模型:实现准确与安全交易

Digits micro-model for accurate and secure transactions

University of Illinois, Chicago(伊利诺伊大学芝加哥分校);Vail Systems, Inc.(Vail Systems公司);Illinois Institute of Technology(伊利诺伊理工学院)

Chirag Chhablani, Nikhita Sharma, Jordan Hosier, Vijay K. Gurbani

AI总结:

本研究提出用于金融领域多位数识别的专用微模型,以低资源消耗实现高准确率,错误率1.8%优于Whisper的5.8%,内存占用仅0.66 GB,支持本地部署保障数据隐私。

摘要:

自动语音识别(ASR)系统在金融领域被用于通过实现自然语言理解和促进高效、直观的交互来增强来电者体验。ASR系统的日益普及要求此类系统具有极低的错误率。用于收集数字数据的主流ASR模型是大型通用商业模型——如Google语音转文本(STT)或Amazon Transcribe——或开源模型(如OpenAI的Whisper)。此类ASR模型在数十万小时的音频数据上训练,运行需要大量资源。尽管大型语音识别模型近期取得了进展,我们强调更小、专门化的“微”模型的潜力。这种轻量模型可以在数字识别特定任务上训练得表现良好,与Whisper或Google STT等通用模型竞争,同时训练时间少于80分钟,占用内存资源至少少一个数量级。此外,与大型语音识别模型不同,微模型在精心选择和策划的数据集上训练,使其高度准确、灵活且易于重新训练,同时使用较低的计算资源。我们展示了为多位数数字识别创建微模型的工作,这些模型处理反映真实世界发音模式的各种说话风格。我们的工作为领域特定的ASR模型做出贡献,提高数字识别准确性和数据隐私。一个额外优势是,其低资源消耗使其可以本地部署,保持私有数据本地化,而不是上传到外部云。我们的结果表明,我们的微模型在识别数字方面比最优秀的商业或开源ASR系统错误更少(我们最佳微模型的错误率为1.8%,而Whisper为5.8%),且内存占用低(我们模型为0.66 GB VRAM,而Whisper为11 GB VRAM)。

英文摘要:

Automatic Speech Recognition (ASR) systems are used in the financial domain to enhance the caller experience by enabling natural language understanding and facilitating efficient and intuitive interactions. Increasing use of ASR systems requires that such systems exhibit very low error rates. The predominant ASR models to collect numeric data are large, general-purpose commercial models -- Google Speech-to-text (STT), or Amazon Transcribe -- or open source (OpenAI's Whisper). Such ASR models are trained on hundreds of thousands of hours of audio data and require considerable resources to run. Despite recent progress large speech recognition models, we highlight the potential of smaller, specialized "micro" models. Such light models can be trained perform well on number recognition specific tasks, competing with general models like Whisper or Google STT while using less than 80 minutes of training time and occupying at least an order of less memory resources. Also, unlike larger speech recognition models, micro-models are trained on carefully selected and curated datasets, which makes them highly accurate, agile, and easy to retrain, while using low compute resources. We present our work on creating micro models for multi-digit number recognition that handle diverse speaking styles reflecting real-world pronunciation patterns. Our work contributes to domain-specific ASR models, improving digit recognition accuracy, and privacy of data. An added advantage, their low resource consumption allows them to be hosted on-premise, keeping private data local instead uploading to an external cloud. Our results indicate that our micro-model makes less errors than the best-of-breed commercial or open-source ASRs in recognizing digits (1.8% error rate of our best micro-model versus 5.8% error rate of Whisper), and has a low memory footprint (0.66 GB VRAM for our model versus 11 GB VRAM for Whisper).

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。

↑