To avoid interference from unexpected background noises and obtain high fidelity voice signal, acoustic sensors with high sensitivity, flat frequency response and high signal-to-noise ratio (SNR) are urgently needed for voice recognition. Graphene-oxide (GO) has received extensive attention due to its advantages of controllable thickness and high fracture strength. However, low mechanical sensitivity (S_M) introduced by undesirable initial stress limits the performance of GO material in the field of voice recognition. To alleviate the aforementioned issue, GO diaphragm with annular corrugations is proposed. By means of the reusable copper mold machined by picosecond laser, the fabrication and transfer of corrugated GO diaphragm are realized, thus achieving a Fabry-Perot (F-P) acoustic sensor. Benefitting from the structural advantage of the corrugated GO diaphragm, our F-P acoustic sensor exhibits high S_M (43.70 nm/Pa@17 kHz), flat frequency response (-3.2 dB to 3.7 dB within 300 Hz~3500 Hz), and high Signal to Noise Ratio (SNR) (76.66 dB@1 kHz). In addition, further acoustic measurements also demonstrate other merits, including an excellent frequency detection resolution (0.01 Hz) and high time stability (output relative variation less than 6.7% for 90 min). Given the merits presented before, the fabricated F-P acoustic sensor with corrugated GO diaphragm can serve as a high-fidelity platform for acoustic detection and voice recognition. In conjunction with the deep residual learning framework, high recognition accuracy of 98.4% is achieved by training and testing the data recorded by the fabricated F-P acoustic sensor.