Towards a software-radio enabled broadcast media navigator

New consumer services are transforming the Hertzian broadcast media into a rich source of multimedia content. A broadcast media navigator combining software radio elements with audio indexing techniques and digital audio recording is proposed. Results from a PC-based demonstrator implementing a simple speech/music discriminator are presented.

[1]  Noel E. O'Connor,et al.  Speech-music discrimination from MPEG-1 bitstream , 2001 .

[2]  Malcolm Slaney,et al.  Construction and evaluation of a robust multifeature speech/music discriminator , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Steve Renals,et al.  Retrieval of broadcast news documents with the THISL system , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[4]  Ton Kalker,et al.  Issues with digital watermarking and perceptual hashing , 2001, SPIE ITCom.

[5]  Zhu Liu,et al.  Classification TV programs based on audio information using hidden Markov model , 1998, 1998 IEEE Second Workshop on Multimedia Signal Processing (Cat. No.98EX175).

[6]  Kate Knill,et al.  Fast implementation methods for Viterbi-based word-spotting , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[7]  Eric D. Scheirer,et al.  Music Content Analysis through Models of Audition , 1998 .

[8]  Liang Gu,et al.  Robust singing detection in speech/music discriminator design , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[9]  Jaap A. Haitsma,et al.  Robust Audio Hashing for Content Identification , 2001 .

[10]  Barry Vercoe,et al.  Folk Music Classification Using Hidden Markov Models , 2001 .

[11]  Karen Spärck Jones,et al.  Acoustic indexing for multimedia retrieval and browsing , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.