Automatic speech recognition performance for training on noised speech

机译：自动语音识别性能，可针对受干扰的语音进行训练

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Performances of some training techniques of automatic speech recognition system are compared in this paper. Speech recognition accuracy was used as measure of performance. Different kinds of outdoor and indoor noise were used for studying. It is shown the superiority of training on noised speech methods over the competitive technique of training on clear speech. It has been found that training by means of noised speech allows reach high, abut 95...97%, recognition accuracy for about 5...10 dB signal-to-noise ratio. At the same time, training by means of clean speech allows reach the same accuracy for about 20...25 dB.

机译：比较了自动语音识别系统的一些训练技术的性能。语音识别准确度用作性能的度量。研究使用了各种室外和室内噪声。它显示了有噪声的语音方法训练比有声语音训练的竞争技术优越。已经发现，通过有声语音的训练允许达到高的，约95 ... 97％的，约5 ... 10 dB的信噪比的识别精度。同时，通过干净的语音进行训练可以达到大约20 ... 25 dB的相同精度。

著录项

来源
《2017 2nd International Conference on Advanced Information and Communication Technologies》|2017年|71-74|共4页
会议地点 Lviv(UA)
作者
Arkadiy Prodeus; Kateryna Kukharicheva;
展开▼
作者单位

Acoustics and Electroacoustics Department, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine;

Acoustics and Electroacoustics Department, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Speech; Automatic speech recognition; Training;

机译：语音;自动语音识别;培训;

相似文献

外文文献
中文文献
专利

1. The relationship between speech recognition in noise and non-speech recognition in noise test performances: Implications for central auditory processing disorders testing [J] . Vermiglio Andrew J., Velappan Keerthana, Heeke Paige, Journal of communication disorders . 2019,第期

机译：噪声测试表演中噪声识别与非语音识别的关系：中央听觉处理障碍测试的影响
2. Noise Adaptive Training for Robust Automatic Speech Recognition [J] . Kalinli O., Seltzer M. L., Droppo J., Audio, Speech, and Language Processing, IEEE Transactions on . 2010,第8期

机译：噪声自适应训练，实现鲁棒的自动语音识别
3. Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition [J] . Shimada Kazuki, Bando Yoshiaki, Mimura Masato, Audio, Speech, and Language Processing, IEEE/ACM Transactions on . 2019,第5期

机译：基于多通道NMF信息波束形成的无监督语音增强技术，用于强噪声自动语音识别
4. Automatic speech recognition performance for training on noised speech [C] . Arkadiy Prodeus, Kateryna Kukharicheva International Conference on Advanced Information and Communication Technologies . 2017

机译：自动语音识别性能，用于培训中发表讲话
5. Compressive nonlinearity for representing speech spectral magnitude to improve noise robustness of automatic speech recognition . [D] . Wong, Brian. 2011

机译：压缩非线性表示语音频谱幅度提高语音自动识别的鲁棒性。
6. Effects of Long-Term Training on Aided Speech-Recognition Performance in Noise in Older Adults [O] . Matthew H. Burk, Larry E. Humes -1

机译：长期训练对老年人语音辅助语音识别性能的影响
7. Noise adaptive training using a vector taylor series approach for noise robust automatic speech recognition [O] . Ozlem Kalinli, Michael L. Seltzer, Alex Acero 2009

机译：使用矢量泰勒级数方法进行噪声自适应训练，用于噪声鲁棒自动语音识别

Automatic speech recognition performance for training on noised speech

摘要

著录项

相似文献

相关主题

期刊订阅