Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as healthcare and news. In this paper, we evaluate the impact of joint training of the retriever and generator components of RAG for the task of domain adaptation in ODQA. We propose RAG-end2end, an extension to RAG that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training. In addition, we introduce an auxiliary training signal to inject more domain-specific knowledge. This auxiliary signal forces RAG-end2end to reconstruct a given sentence by accessing the relevant information from the external knowledge base. Our novel contribution is that, unlike RAG, RAG-end2end does joint training of the retriever and generator for the end QA task and domain adaptation. We evaluate our approach with datasets from three domains: COVID-19, News, and Conversations, and achieve significant performance improvements compared to the original RAG model. Our work has been open-sourced through the HuggingFace Transformers library, attesting to our work’s credibility and technical consistency.

Traditionally, speech emotion recognition (SER) research has relied on manually handcrafted acoustic features using feature engineering. However, the design of handcrafted features for complex SER tasks requires significant manual eort, which impedes generalisability and slows the pace of innovation. This has motivated the adoption of representation learning techniques that can automatically learn an intermediate representation of the input signal without any manual feature engineering. Representation learning has led to improved SER performance and enabled rapid innovation. Its effectiveness has further increased with advances in deep learning (DL), which has facilitated \textit{deep representation learning} where hierarchical representations are automatically learned in a data-driven manner. This paper presents the first comprehensive survey on the important topic of deep representation learning for SER. We highlight various techniques, related challenges and identify important future areas of research. Our survey bridges the gap in the literature since existing surveys either focus on SER with hand-engineered features or representation learning in the general setting without focusing on SER.

Deep learning-based cardiac auscultation is of significant interest to the healthcare community as it can help reducing the burden of manual auscultation with automated detection of abnormal heartbeats. However, the problem of automatic cardiac auscultation is complicated due to the requirement of reliable and highly accurate systems, which are robust to the background noise in the heartbeat sound. In this paper, we propose a Recurrent Neural Networks (RNNs)-based automated cardiac auscultation solution. Our choice of RNNs is motivated by their great success of modeling sequential or temporal data even in the presence of noise. We explore the use of various RNN models, and demonstrate that these models significantly outperform the best reported results in the literature. We also present the run-time complexity of various RNNs, which provides insight about their complexity versus performance trade-offs.

Emotional voice conversion (EVC) seeks to convert the emotional state of an utterance while preserving the linguistic content and speaker identity. In EVC, emotions are usually treated as discrete categories overlooking the fact that speech also conveys emotions with various intensity levels that the listener can perceive. In this work, we aim to explicitly characterize and control the intensity of emotion. We propose to disentangle the speaker style from linguistic content and encode the speaker style into a style embedding in a continuous space that forms the prototype of emotion embedding. We further learn the actual emotion encoder from an emotion-labelled database and study the use of relative attributes to represent fine-grained emotion intensity. To ensure emotional intelligibility, we incorporate emotion classification loss and emotion embedding similarity loss into the training of the EVC network. As desired, the proposed network controls the fine-grained emotion intensity in the output speech. Through both objective and subjective evaluations, we validate the effectiveness of the proposed network for emotional expressiveness and emotion intensity control.

The mHealth trend, which uses mobile devices and associated technology for health interventions, offers unprecedented opportunity to transform the health services available to people across the globe. In particular, the mHealth transformation can be most disruptive in the developing countries, which is often characterized by a dysfunctional public health system. Despite this opportunity, the growth of mHealth in developing countries is rather slow and no existing studies have conducted an in-depth search to identify the reasons. We present a comprehensive report about the factors hindering the growth of mHealth in developing countries. Most importantly, we outline future strategies for making mHealth even more effective. We are also the first to conduct a case study on the public health system of Pakistan showing that mHealth can offer tremendous opportunities for a developing country with a severe scarcity of health infrastructure and resources. The findings of this paper will guide the development of policies and strategies for the sustainable adoption of mHealth not only in Pakistan but also for any developing country in general.