On-line Speech Enhancement by Time-Frequency Masking under Prior Knowledge of Source Locati.pdfVIP

下载本文档

3
0
约2.57万字
约 6页
2017-04-11 发布于江苏
举报
版权申诉

On-line Speech Enhancement by Time-Frequency Masking under Prior Knowledge of Source Locati.pdf

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

On-line Speech Enhancement by Time-Frequency Masking under Prior Knowledge of Source Locati

Abstract—This paper presents the source extraction system which can extract only target signals with constraints on source localization in on-line systems. The proposed system is a kind of methods for enhancing a target signal and suppressing other interference signals. But, the performance of proposed system is superior to any other methods and the extraction of target source is comparatively complete. The method has a beamforming concept and uses an improved time-frequency (TF) mask-based BSS algorithm to separate a target signal from multiple noise sources. The target sources are assumed to be in front and test data was recorded in a reverberant room. The experimental results of the proposed method was evaluated by the PESQ score of real-recording sentences and showed a noticeable speech enhancement. Keywords—Beamforming, Non-stationary noise reduction, Source separation, TF mask. I. INTRODUCTION PEECH enhancement algorithms are used to increase the recognition rates and improve the quality of services. They are concerned with the processing of noisy speech to improve the quality of the signal. Stationary noise reduction has been achieved through various techniques including Wiener and Kalman filtering. But non-stationary noises including speech or music signals cannot be effectively reduced. Microphone array-based speech enhancement has been recently spotlighted because of its wide usability such as high-quality hands-free telecommunication systems and its powerfulness in reducing non-stationary noises. In a sense, we can think of the microphone array-based algorithms as a kind of target source extraction systems. The conventional source extraction system is achieved by the generalized sidelobe canceller (GSC). It is considered the most practical algorithm because of its simplicity and effectiveness [1]-[3]. But it has some insufficiency in noise reduction. Also, the blind source separation (BSS) can be used for the ta