Rescoring by a deep neural network for spoken term detection-猫眼课题宝

DOI：

10.1109/apsipa.2015.7415465

发表时间：

2015-12

期刊：

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Ryota Kon'no;K. Kojima;Kazuyo Tanaka;Shi-wook Lee;Y. Itoh

在口语词检测（STD）中，词汇表外（OOV）查询词的检测是至关重要的，因为查询词很可能是OOV词。本文提出了一种重新评分方法，该方法使用深度神经网络（DNN）输出的后验概率来提高OOV查询词的检测准确率。用于OOV查询项的常规STD方法通过使用自动语音识别器来搜索语音数据的子字序列的查询子字序列。所提出的方法中的详细匹配是通过使用DNN输出的概率来执行的。生成帧或状态级别的伪查询，以便在帧级别对齐所获得的概率。为了减少DNN的计算负担，我们只将所提出的方法应用于顶部候选话语，这可以通过传统的STD方法快速找到。实验进行了评估所提出的方法的性能，使用开放的测试集合的SpokenDoc任务的NTCIR-9和NTCIR-10研讨会作为基准。所提出的方法提高了5至20点之间的平均精度，超过了在车间获得的最佳精度。这些结果证明了所提出的方法的有效性。

In spoken-term detection (STD), the detection of out-of-vocabulary (OOV) query terms is crucial because query terms are likely to be OOV terms. This paper proposes a rescoring method that uses the posterior probabilities output by a deep neural network (DNN) to improve detection accuracy for OOV query terms. Conventional STD methods for OOV query terms search a query subword sequence for subword sequences of speech data by using an automatic speech recognizer. A detailed matching in the proposed method is performed by using the probabilities output by the DNN. A pseudo query at the frame or state level is generated so as to align the obtained probability at the frame level. To reduce the computational burden on the DNN, we apply the proposed method to only top candidate utterances, which can be quickly found by a conventional STD method. Experiments were conducted to evaluate the performance of the proposed method, using the open test collections for the SpokenDoc tasks of the NTCIR-9 and NTCIR-10 workshops as benchmarks. The proposed method improved the mean average precision between 5 and 20 points, surpassing the best accuracy obtained at the workshops. These results demonstrated the effectiveness of the proposed method.

Rescoring by a deep neural network for spoken term detection

文献摘要

相似文献