Design and Implementation of a Fixed-Mobile Convergent Music Search Engine (FMC-MUSE)

Query by Singing/Humming (QBSH) is a most natural way for music search. A music search system can help music finders search songs by matching a part of melody by singing or humming. Many music information retrieval techniques have been developed to carry out music search for years. On the other hand, thanks to the rapid growth of mobile wireless Internet technologies this decade, music search applications can be implemented on hand-carried devices, such as cellular phones, to conduct music search anytime and anywhere via any available networks, such as Wi-Fi, UMTS, WiMAX to the emerging 3GPP-LTE networks. In the past, little studies had ever been revealed about how to design and implement a lightweight music search engine over a fixed or mobile Internet. In this article, we aim to elaborate a practical skeleton of developing a simple music search engine over fixed or mobile networks—a Fixed-Mobile Convergent Music Search Engine (FMC-MUSE). FMC-MUSE can process music queries by QBSH from fixed or mobile clients and return a dataset containing the search results and meta-info back to music finders via ubiquitous networks.

[1]  Jyh-Shing Roger Jang,et al.  Super MBox: an efficient/effective content-based music retrieval system , 2001, MULTIMEDIA '01.

[2]  Bao-Gang Hu,et al.  An Implementation of Web Based Query by Humming System , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[3]  Remco C. Veltkamp,et al.  A Survey of Music Information Retrieval Systems , 2005, ISMIR.

[4]  Silviu Ciochina,et al.  An improved spectral subtraction method for speech enhancement using a perceptual weighting filter , 2008, Digit. Signal Process..

[5]  Simona Halunga,et al.  Nonlinear spectral subtraction method for colored noise reduction using multi-band Bark scale , 2008, Signal Process..

[6]  Magnus Westerlund,et al.  Real-Time Transport Protocol (RTP) Payload Format and File Storage Format for the Adaptive Multi-Rate (AMR) and Adaptive Multi-Rate Wideband (AMR-WB) Audio Codecs , 2002, RFC.

[7]  Hong-Ru Lee,et al.  Approximate lower-bounding functions for the speedup of DTW for melody recognition , 2005, 2005 9th International Workshop on Cellular Neural Networks and Their Applications.

[8]  Stan Salvador,et al.  FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space , 2004 .

[9]  Philip Chan,et al.  Toward accurate dynamic time warping in linear time and space , 2007, Intell. Data Anal..

[10]  Jyh-Shing Roger Jang,et al.  A General Framework of Progressive Filtering and Its Application to Query by Singing/Humming , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Magnus Westerlund,et al.  RTP Payload Format and File Storage Format for the Adaptive Multi-Rate (AMR) and Adaptive Multi-Rate Wideband (AMR-WB) Audio Codecs , 2007, RFC.