The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowding effect, adjacency, fatigue, task difficulty, and required large number of trials for character recognition. For P300 detection, deep learning algorithms have shown the state of art performance compared to the conventional machine learning algorithms in the recent past. Therefore, authors have been motivated to develop a deep learning architecture for DS-based P300 speller which can detect the target characters more accurately and in less number of trials. For this, two proven deep learning algorithms, stacked autoencoder (SAE) and deep convolution neural network (DCNN) have been adopted. For further bettering their performances, batch normalization and innovative double batch training is included here to achieve accelerated training and alleviate the problem of overfitting. Additionally, a leaky ReLU activation function has also been used in DCNN to overcome dying ReLU problem. The experiments have been performed on self-generated dataset of 20 Devanagari words with 79 characters acquired from 10 subjects using 16 channel actiCAP Xpress EEG recorder. The experimental results illustrated that the proposed DCNN is able to detect 88.22% correct targets in just three trials. Moreover, it also provides ITR of 20.58 bits per minutes, which is significantly higher than existing techniques.