Code-switched (CS) data is ubiquitous in today's globalized world, but the dearth of annotated datasets in code-switching poses a significant challenge for learning diverse tasks across different language pairs.Parameter-efficient prompt-tuning approaches conditioned on frozen language models have shown promise for transfer learning in limited-resource setups.In this paper, we propose a novel instancebased prompt composition technique, PRO-CS, for CS tasks that combine language and task knowledge.We compare our approach with prompt-tuning and fine-tuning for codeswitched tasks on 10 datasets across 4 language pairs.Our model outperforms the prompttuning approach by significant margins across all datasets and outperforms or remains at par with fine-tuning by using just 0.18% of total parameters.We also achieve competitive results when compared with the fine-tuned model in the low-resource cross-lingual and crosstask setting, indicating the effectiveness of our approach to incorporate new code-switched tasks.

We propose a novel framework which combines the input-conditioned filter generation module and a decoder based network to incorporate contextual information present in images into Convolutional Neural Networks (CNNs). In contrast to traditional CNNs, we do not employ the same set of learned convolution filters for all input image instances. And our proposed decoder network serves the purpose of reducing the transformation present in the input image by learning to construct a representative image of the input image class. Our proposed joint supervision of input-aware framework when combined with techniques inspired by Multi-instance learning and max-pooling, results in a transformation-invariant neural network. We investigated the performance of our proposed framework on three MNIST variations, which covers both rotation and scaling variance, and achieved 0.98% error on MNIST-rot-12k, 1.12% error on Half-rotated MNIST and 0.68% error on Scaling MNIST, which is significantly better than the state-of-the-art results. Our proposed model also showcased consistent improvement on the CIFAR dataset. We make use of visualization to further prove the effectiveness of our input-aware convolution filters. Our proposed convolution filter generation framework can also serve as a plugin for any CNN based architecture and enhance its modeling capacity.

This research proposes a Deep Neural Network architecture for Speech Emotion Recognition called Emoception, which takes inspiration from Inception modules. The network takes speech features like Mel-Frequency Spectral Coefficients (MFSC) or Mel-Frequency Cepstral Coefficients (MFCC) as input and recognizes the relevant emotion in the speech. We use USC-IEMOCAP dataset for training but the limited amount of training data and large depth of the network makes the network prone to overfitting, reducing validation accuracy. The Emoception network overcomes this problem by extending in width without increase in computational cost. We also employ a powerful regularization technique, Multi-Task Learning (MTL) to make the network robust. The model using MFSC input with MTL increases the accuracy by 1.6% vis-à-vis Emoception without MTL. We report an overall accuracy improvement of around 4.6% compared to the existing state-of-art methods for four emotion classes on IEMOCAP dataset.