Automatically transcribing meetings using distant microphones

Automatically transcribing meetings using distant microphones
复制标题

使用远程麦克风自动转录会议

DOI:
10.1109/icassp.2005.1415282
复制
发表时间:
2005
期刊:
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
影响因子:
--
通讯作者:
A. Waibel
A. Waibel
中科院分区:
--
文献类型:
--
作者:
Florian Metze;C. Fügen;Yue Pan;A. Waibel

文献摘要

被引文献

相似文献

在本文中,我们描述了我们的努力,以发展声学模型适合于远距离麦克风自动语音识别。我们的目标是研究如何优化在近距离说话和远距离麦克风数据的组合上训练的系统的性能,同时假设尽可能少的关于(多个)远距离麦克风的配置的信息,以避免猜测和冗长的校准运行。我们在NIST的RT-04 S“会议”语音到文本评估中评估了我们的系统,其中语音数据在几个站点使用不同数量的不同桌面麦克风记录,但不使用麦克风阵列。安装在身体上的麦克风提供了远距离ASR性能的基线数字,并允许将会议语音与其他自发语音数据进行比较。
In this paper, we describe our efforts to develop acoustic models suitable for distant microphone automatic speech recognition. Our goal is to investigate how the performance of a system trained on a combination of close-talking and distant microphone data can be optimized, while assuming as little information about the configuration of (multiple) distant microphones as possible, to avoid guesstimates and lengthy calibration runs. We evaluated our system in NIST's RT-04S "Meeting" speech-to-text evaluation, where speech data was recorded at several sites with a varying number of different table-top microphones, but not with microphone arrays. Body-mounted microphones provide baseline numbers for distant ASR performance and allow for comparisons of meeting speech with other spontaneous speech data.