A novel sparse channel state information (CSI) estimation scheme is proposed for orthogonal time frequency space (OTFS) modulated systems, in which the pilots are directly transmitted over the time-frequency (TF)-domain grid for estimating the delay-Doppler (DD)-domain CSI. The proposed CSI estimation model leads to a reduction in the pilot overhead as well as the training duration required. Furthermore, it does not require a DD-domain guard interval between the pilot and data symbols, hence increasing the bandwidth efficiency. A novel Bayesian learning (BL) framework is proposed for CSI acquisition, which exploits the DD-domain sparsity for improving the estimation accuracy in comparison to the conventional minimum mean squared error (MMSE)-based scheme. A lowcomplexity linear MMSE detector is used in the subsequent data detection phase. Our simulation results demonstrate the performance improvement of the proposed BL-based scheme over the conventional MMSE-based scheme as well as over other existing sparse estimation schemes. Index Terms-OTFS, delay-Doppler domain channel, sparsity, channel estimation, BCRLB, high-mobility
I. INTRODUCTIONGiven the continuously evolving diverse range of applications, it is of paramount importance to explore novel modulation techniques that are resilient to both the delay-spread and to the Doppler-shifts introduced by the wireless propagation medium. To this end, a novel delay-Doppler (DD)-domain modulation technique, originally proposed by R. , termed as the orthogonal time frequency space (OTFS) arrangement, deserves further exploration in highmobility scenarios. An important aspect of OTFS modulation is that it relies on the DD-domain representation of the wireless