Optical single-sideband (SSB) transmission enhances spectral efficiency and mitigates transmission reach limitations caused by chromatic dispersion (CD), making it ideal for cost-effective data-center interconnects. This paper proposes and demonstrates deep neural network (DNN)-enabled optical performance monitoring (OPM) for optical SSB transmissions. By extracting features dependent on both carrier-to-signal power ratio (CSPR) and optical signal-to-noise ratio (OSNR) from amplitude histograms (AHs) generated by an AC-coupled photodetector (PD) and an analog-to-digital converter (ADC), a low-complexity dual-task DNN (DT-DNN) is employed to jointly estimate CSPR and OSNR with high accuracy. Numerical results show that for a 50 GBaud 16-QAM SSB signal, the root mean square error (RMSE) values for CSPR estimation (2-11 dB range) and OSNR estimation (14-23 dB range) are 0.14 dB and 0.29 dB, respectively, under back-to-back (B2B) transmission. After transmission over 80 km of standard single-mode fiber (SSMF), the corresponding RMSE values increase to 0.17 dB and 0.33 dB, respectively. Experimental validation using a 25 GBaud 16-QAM SSB signal over 40 km of SSMF yields RMSE values for CSPR and OSNR estimation of less than 0.26 dB and 0.80 dB, respectively. The proposed technique shows great potential for real-time OPM in high-speed optical SSB transmission systems.