In this paper, we propose a new approach for the estimation of the channel parameters under In-phase/ Quadrature (IQ) impairments, where the term channel refers to any transformation occurring between the transmitter and receiver IQ impairments. While most of the available strategies for channel estimation under IQ impairments are based on the Least-Squares (LS) approach, we propose a new estimator based on the Maximum Likelihood (ML) technique. We show that a simple estimator obtained from the ML gives better statistical performance than any LS-based technique while having a significant lower computational complexity. Mathematically, the proposed ML-based estimator is obtained from the minimization of the smallest eigenvalue of a particular 2 × 2 matrix. Simulations show the benefit of the proposed approach for the estimation of the Carrier Frequency Offset (CFO) and for the estimation of Finite Impulse Response (FIR) channel coefficients under both transmitter and receiver IQ impairments.