The algorithm was next tested on single channel simultaneous speech signals spoken by two speakers. Each speech signal file was artificially created by mixing two independent speech signals with 0 dB signal-to-signal ratio. To evaluate our algorithm objectively, we also applied cepstrum for comparison. Note that cepstrum is not strictly designed as a multi-pitch detector, however. Results with cepstrum are shown in table 2 and results with our algorithm are shown in table 3. An example of detected contours is depicted in Fig 6 where the reference is shown in Fig 7. Pairs of speech files by which concurrent speech signals were created are shown in the first and second columns in table 2 and 3. As the results, our algorithm significantly outperformed cepstrum as well and showed high performance.
Some of the gross errors were found at the first process mainly because of unvoiced consonants. Since we focused only on harmonic structure, it was difficult to avoid the gross errors caused by them. Meanwhile, when the two simultaneous speakers were male and female, male rather resulted worse. At the second process stated in Section 3, AIC rather prefers to be positioned in as higher frequency as it can because the number of free parameters can be lessen. Accordingly, if both pitch and amplitude of one utterence was specificially lower than another, it tended to be ignored.