Building Keyword Search System from End-To-End Asr Systems
Building Keyword Search System from End-To-End Asr Systems
复制标题
DOI：
10.1109/icassp49357.2023.10097249
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Ruizhe Huang;Matthew Wiesner;Leibny Paola García-Perera;Daniel Povey;J. Trmal;S. Khudanpur
中科院分区：
文献类型：
--
作者：
Ruizhe Huang;Matthew Wiesner;Leibny Paola García-Perera;Daniel Povey;J. Trmal;S. Khudanpur
关键词搜索（KWS）系统通常建立在现有的自动语音识别（ASR）系统之上。然而，端到端（E2 E）ASR模型并不自然地配备有字级定时信息或置信度。现有的用于为KWS重新利用E2 E ASR系统的方法主要是启发式的或特定于模型的。在本文中，我们描述了一个通用的KWS管道，适用于任何ASR模型，产生N-最好的列表。我们使用外部字对齐器或基于时间保持加权有限状态传感器的解码器提取时序信息。我们表明，我们的轻量级，ASR不可知的方法的置信度估计的基础上N-最好的列表优于其他常用的算法，如使用解码器的softmax概率，甚至更复杂的专用置信度估计模型（CEM）。最后，我们将我们的性能与混合ASR模型进行了比较，广泛评估了单词级时间，信心和召回对KWS性能的影响。我们的KWS管道可在线使用1，适合于评估上述ASR组件作为下游任务。
Keyword search (KWS) systems are commonly built on top of existing automatic speech recognition (ASR) systems. However, end-to-end (E2E) ASR models are not naturally equipped with word-level timing information or confidence. Existing methods for re-purposing E2E ASR systems for KWS are largely heuristic or model-specific. In this paper, we describe a general KWS pipeline, applicable to any ASR model that generates N-best lists. We extract timing information using either external word-aligners, or time-preserving weighted finite-state transducer-based decoders. We show that our light-weight, ASR-agnostic approach for confidence estimation based on N-best lists outperforms other commonly used heuristics, such as using the decoder’s softmax probability, and even a more complicated dedicated confidence estimation model (CEM). Finally, we compare our performance to hybrid ASR models, extensively evaluating the impact of word-level timing, confidence, and recall on KWS performance. Our KWS pipeline is available online1, suitable for evaluating the aforementioned ASR components as downstream tasks.