In the domain of speech recognition many methods have been proposed over time like Gaussian mixture models (GMM), GMM with universal background model (GMM-UBM framework), joint factor analysis, etc. i-Vector subspace modeling is one of the recent methods that has become the state of the art technique in this domain. This method largely provides the benefit of modeling both the intra-domain and inter-domain variabilities into the same low dimensional space. In this survey, we present a comprehensive collection of research work related to i-vectors since its inception. Some recent trends of using i-vectors in combination with other approaches are also discussed. The application of i-vectors in various fields of speech recognition, viz speaker, language, accent recognition, etc. is also presented. This paper should serve as a good starting point for anyone interested in working with i-vectors for speech processing in general. We then conclude the paper with a brief discussion on the future of i-vectors.

How can we measure the generalization of models to a variety of unseen tasks when provided with their language instructions? To facilitate progress in this goal, we introduce NATURAL-INSTRUCTIONS v2 , a benchmark of 1,600+ diverse language tasks and their expertwritten instructions. It covers 70+ distinct task types, such as tagging, in-filling, and rewriting. These tasks are collected with contributions of NLP practitioners in the community and through an iterative peer review process to ensure their quality. With this large and diverse collection of tasks, we are able to rigorously benchmark cross-task generalization of models-training on a subset of tasks and evaluating on the remaining unseen ones. For instance, we quantify generalization as a function of various scaling parameters, such as the number of observed tasks, the number of instances, and model sizes. Based on these insights, we introduce Tk-INSTRUCT, an encoder-decoder Transformer that is trained to follow a variety of in-context instructions (plain language task definitions or k-shot examples) which outperforms existing larger models on our benchmark. We hope this benchmark facilitates future progress toward more general-purpose language understanding models. 1

No abstract

BackgroundThe emergence of coronavirus disease (COVID-19) as a global pandemic has resulted in the loss of many lives and a significant decline in global economic losses. Thus, for a large country like India, there is a need to comprehend the dynamics of COVID-19 in a clustered way.ObjectiveTo evaluate the clinical characteristics of patients with COVID-19 according to age, gender, and preexisting comorbidity. Patients with COVID-19 were categorized according to comorbidity, and the data over a 2-year period (1 January 2020 to 31 January 2022) were considered to analyze the impact of comorbidity on severe COVID-19 outcomes.MethodsFor different age/gender groups, the distribution of COVID-19 positive, hospitalized, and mortality cases was estimated. The impact of comorbidity was assessed by computing incidence rate (IR), odds ratio (OR), and proportion analysis.ResultsThe results indicated that COVID-19 caused an exponential growth in mortality. In patients over the age of 50, the mortality rate was found to be very high, ~80%. Moreover, based on the estimation of OR, it can be inferred that age and various preexisting comorbidities were found to be predictors of severe COVID-19 outcomes. The strongest risk factors for COVID-19 mortality were preexisting comorbidities like diabetes (OR: 2.39; 95% confidence interval (CI): 2.31–2.47; p < 0.0001), hypertension (OR: 2.31; 95% CI: 2.23–2.39; p < 0.0001), and heart disease (OR: 2.19; 95% CI: 2.08–2.30; p < 0.0001). The proportion of fatal cases among patients positive for COVID-19 increased with the number of comorbidities.ConclusionThis study concluded that elderly patients with preexisting comorbidities were at an increased risk of COVID-19 mortality. Patients in the elderly age group with underlying medical conditions are recommended for preventive medical care or medical resources and vaccination against COVID-19.

No abstract