Improving Black-box Speech Recognition using Semantic Parsing
Improving Black-box Speech Recognition using Semantic Parsing
复制标题
DOI：
--
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Rodolfo Corona;Jesse Thomason;R. Mooney
中科院分区：
文献类型：
--
作者：
Rodolfo Corona;Jesse Thomason;R. Mooney
语音是机器人和消费应用中人机交互的自然渠道。从语音开始的自然语言理解管道可能难以从语音识别错误中恢复。专为通用用途而构建的黑盒自动语音识别 (ASR) 系统无法利用域内语言模型，否则可以改善这些错误。在这项工作中，我们提出了一种使用域内语言模型和针对特定任务训练的语义解析器对黑盒 ASR 假设进行重新排序的方法。与最先进的 ASR 普通输出相比，我们的重新排序方法显着提高了转录准确性和语义理解。
Speech is a natural channel for human-computer interaction in robotics and consumer applications. Natural language understanding pipelines that start with speech can have trouble recovering from speech recognition errors. Black-box automatic speech recognition (ASR) systems, built for general purpose use, are unable to take advantage of in-domain language models that could otherwise ameliorate these errors. In this work, we present a method for re-ranking black-box ASR hypotheses using an in-domain language model and semantic parser trained for a particular task. Our re-ranking method significantly improves both transcription accuracy and semantic understanding over a state-of-the-art ASR’s vanilla output.