Recordings of broadcast audio content often contain errors (e.g., noise, signal loss, interference, talkover). A method and apparatus are provided for improving the quality of such a recording. Multiple recordings of a broadcast audio program are identified, and are aligned according to some time index of the program, such as the beginning, midpoint or end of one of the recordings. Samples of each recording are taken and compared. If a majority (or plurality) of the samples agree (e.g., they match within an allowable threshold of variance), one of them is used to generate or populate a new recording. If there is no majority (or plurality), one of the samples may be chosen at random, on the basis of which recording has most often been in the majority (or plurality), or on some other basis. Or, the method may be repeated or extended to obtain samples of other recordings.