本文選題：音頻感知哈希 + Gammachirp濾波器組　； 參考：《華東理工大學(xué)》2015年碩士論文

【摘要】：隨著互聯(lián)網(wǎng)和多媒體技術(shù)的不斷發(fā)展,人們能夠越來(lái)越方便的獲取更多的數(shù)字音頻資源。由于人耳聽(tīng)覺(jué)系統(tǒng)對(duì)于音頻具有卓越的分辨能力,即使在嘈雜的環(huán)境中,只需要幾秒鐘便可以識(shí)別出正在播放的歌曲。但問(wèn)題是面對(duì)越來(lái)越多的音頻資源,如何通過(guò)計(jì)算機(jī)實(shí)現(xiàn)自動(dòng)音頻識(shí)別。由此產(chǎn)生了基于內(nèi)容進(jìn)行識(shí)別的音頻感知哈希技術(shù)。 針對(duì)目前很多提出的音頻感知哈希算法魯棒性不夠好,計(jì)算復(fù)雜度高的問(wèn)題,本文提出一種新的音頻感知哈希算法。首先,我們?cè)O(shè)計(jì)了一種新的音頻時(shí)頻域特征表示方法,用多通道Gammachirp濾波器組在人耳最敏感頻帶范圍內(nèi)對(duì)音頻信號(hào)進(jìn)行濾波,分幀后按頻帶計(jì)算能量譜,實(shí)驗(yàn)證明該音頻特征具有很好的魯棒性和抗幾何失真能力。接著利用非負(fù)矩陣分解(Non-negative Matrix Factorization, NMF)提取出Gamamchirp耳蝸能量譜局部特征的同時(shí)對(duì)數(shù)據(jù)進(jìn)行降維。最后對(duì)該局部特征進(jìn)行差分和量化得到二值化的音頻感知哈希,實(shí)驗(yàn)結(jié)果表明在經(jīng)受音頻編輯軟件多種攻擊和實(shí)際環(huán)境中錄音檢索時(shí),所提出的音頻感知哈希算法都具有很高的識(shí)別率。 另一方面,檢索速度在音頻信息檢索中也是一個(gè)很重要的問(wèn)題。僅通過(guò)改變算法無(wú)法在短時(shí)間內(nèi)獲得顯著的速度提升。因此,有必要利用其它計(jì)算設(shè)備加速音頻檢索算法。圖形處理單元(Graphic Processing Unit, GPU)能夠提供強(qiáng)大的并行計(jì)算能力,嘗試?yán)肎PU對(duì)已有音頻檢索算法進(jìn)行加速具有重要的意義。本文中,通過(guò)利用CPU與GPU協(xié)同運(yùn)算使得感知哈希匹配和整個(gè)音頻信息檢索過(guò)程的耗時(shí)得到了大幅度降低。 最后,本文結(jié)合以上算法設(shè)計(jì)了一個(gè)交互式音樂(lè)檢索系統(tǒng),該系統(tǒng)可以通過(guò)錄取幾秒種的音頻片段檢索出其對(duì)應(yīng)的曲名,歌手以及專輯封面圖片等信息。
[Abstract]:With the continuous development of Internet and multimedia technology, people can obtain more and more digital audio resources more and more conveniently.Because the human auditory system has excellent audio discrimination, even in noisy environments, it takes only a few seconds to recognize the songs being played.But the problem is how to realize automatic audio recognition by computer in the face of more and more audio resources.Therefore, an audio perceptive hashing technique based on content recognition is produced.Aiming at the problem that many audio perceptive hashing algorithms are not robust enough and high computational complexity, a new audio perceptual hash algorithm is proposed in this paper.First of all, we design a new time and frequency domain feature representation method for audio frequency. We filter audio signals in the most sensitive frequency band of human ear by using multi-channel Gammachirp filter banks, and calculate the energy spectrum according to the frequency band after dividing frames.Experiments show that the audio feature has good robustness and anti-geometric distortion.Then the non-negative Matrix factorization (NMF) is used to extract the local features of the Gamamchirp cochlear energy spectrum and to reduce the dimension of the data.Finally, the binary audio perceptual hashes are obtained by differential and quantization of the local features. The experimental results show that, when the audio editing software is subjected to various attacks and the actual environment,The proposed audio perceptual hashing algorithm has a high recognition rate.On the other hand, retrieval speed is also an important problem in audio information retrieval.Only by changing the algorithm can not achieve a significant speed increase in a short period of time.Therefore, it is necessary to use other computing devices to speed up the audio retrieval algorithm.Graphic Processing Unit (GPU) can provide powerful parallel computing power. It is of great significance to use GPU to accelerate the existing audio retrieval algorithms.In this paper, the time consuming of perceptual hash matching and the whole audio information retrieval process is greatly reduced by using CPU and GPU cooperative operation.Finally, this paper designs an interactive music retrieval system based on the above algorithms. The system can retrieve the corresponding music titles, singers and album cover pictures by taking audio clips of several seconds.
【學(xué)位授予單位】：華東理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TN713;TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 趙鶴鳴,葛良,陳雪勤,俞一彪;基于聲音定位和聽(tīng)覺(jué)掩蔽效應(yīng)的語(yǔ)音分離研究[J];電子學(xué)報(bào);2005年01期

2 牛夏牧;焦玉華;;感知哈希綜述[J];電子學(xué)報(bào);2008年07期

3 徐達(dá)文;王讓定;鮑吉龍;;基于聽(tīng)覺(jué)感知模型的自適應(yīng)音頻數(shù)字水印算法[J];計(jì)算機(jī)工程與應(yīng)用;2006年31期

4 吳曉婷;閆德勤;;數(shù)據(jù)降維方法分析與研究[J];計(jì)算機(jī)應(yīng)用研究;2009年08期

5 張文q，

本文編號(hào)：1756185