arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.04767eess.AScs.SD
收藏

一种实用的多领域语音识别框架及神经语言建模的实例抽样方法

A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling

Tencent Cloud Xiaowei(腾讯云小微)

Yike Zhang, Xiaobing Feng, Yi Liu, Songjun Cao, Long Ma

摘要:

在智能电话或车辆上使用的自动语音识别(ASR)系统通常需要处理来自非常不同的域的语音查询。在这种情况下,普通的ASR系统通常无法在每个域上都表现良好。本文提出了一个多领域的ASR框架,腾讯地图,一个导航应用程序,用于智能手机和车载信息娱乐系统。该框架由三个核心部分组成:一个基本的ASR模块生成的语音查询的n-最好的列表,一个文本分类模块,以确定语音查询属于哪个域,和一个重排序模块rescore n-最好的列表使用特定于域的语言模型。此外,提出了一种基于实例抽样的神经网络语言模型(NNLM)训练方法,以解决多领域ASR中的数据不平衡问题。在实验中,由于导航和播放音乐是腾讯地图的两个主要功能,因此本文提出的框架在导航领域和音乐领域进行了评估。与一般的ASR系统相比,该框架在从腾讯地图和我们的车载语音助手收集的几个测试集上实现了相对13% $\sim$ 22%的字符错误率降低。

英文摘要:

Automatic speech recognition (ASR) systems used on smart phones or vehicles are usually required to process speech queries from very different domains. In such situations, a vanilla ASR system usually fails to perform well on every domain. This paper proposes a multi-domain ASR framework for Tencent Map, a navigation app used on smart phones and in-vehicle infotainment systems. The proposed framework consists of three core parts: a basic ASR module to generate n-best lists of a speech query, a text classification module to determine which domain the speech query belongs to, and a reranking module to rescore n-best lists using domain-specific language models. In addition, an instance sampling based method to training neural network language models (NNLMs) is proposed to address the data imbalance problem in multi-domain ASR. In experiments, the proposed framework was evaluated on navigation domain and music domain, since navigating and playing music are two main features of Tencent Map. Compared to a general ASR system, the proposed framework achieves a relative 13% $\sim$ 22% character error rate reduction on several test sets collected from Tencent Map and our in-car voice assistant.

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。

↑