A real-time circuit is described which automatically discriminates between speech and music signals. An output of the circuit gives, by means of a fuzzy feature combiner, an estimate of the probability that the input is speech. The discriminator is tested (for both sexes) for various languages, such as English, Danish, Dutch, French, German, and Japanese, against various types of music, such as pop, opera, romantic, baroque, and various solo musical instruments. The discriminator is found to be extremely reliable, the false alarm probability (inferring speech while the input is music) being virtually zero.
|Number of pages||6|
|Journal||Journal of the Audio Engineering Society|
|Publication status||Published - 1 Dec 1999|