Abstract

India is a country with thousands of languages and dialects spoken across a billion-strong population. For multi-lingual content creation and accessibility, text-to-speech systems will play a crucial role. However, the current neural TTS systems are data-hungry and need about 20 hours of clean single-speaker speech data for each language and speaker. This is not scalable for the large number of Indian languages and dialects. In this work, we demonstrate three simple, yet effective pre-training strategies that allow us to train neural TTS systems with just about one-tenth of the data needs while also achieving better accuracy and naturalness. We show that such pre-trained neural TTS systems can be quickly adapted to different speakers across languages and genders with less than 2 hours of data, thus significantly reducing the effort for future expansions to the thousands of rare Indian languages. We specifically …

Abstract

In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state-of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent works using lip movements as additional cues improve the quality of generated speech over" audio-only" methods. But, these methods cannot be used for several applications where the visual stream is unreliable or completely absent. We propose a new paradigm for speech enhancement by exploiting recent breakthroughs in speech-driven lip synthesis. Using one such model as a teacher network, we train a robust student network to produce accurate lip movements that mask away the noise, thus acting as a" visual noise filter". The intelligibility of the speech enhanced by our pseudo-lip approach is comparable (< 3% difference) to the case of using real lips. This implies that we can exploit the advantages of using lip movements even in the absence of a real video stream. We rigorously evaluate our model using quantitative metrics as well as human evaluations. Additional ablation studies and a demo video on our website containing qualitative comparisons and results clearly illustrate the effectiveness of our approach.

Abstract

We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa. org

Abstract

We consider the centralized coded caching system where a library of files is available at the server and their subfiles are cached at the clients as prescribed by a placement delivery array (PDA). We are interested in the problem where a specific file in the library is replaced with a new file at the server, the contents of which are correlated with the file being replaced, and this replacement needs to be communicated to the caches. The server loses the original file when the replacement is done and is unaware of the differences between the two files, whereas each cache has access to specific subfiles of the original file as dictated by the PDA. We model the correlation between the two files by assuming that they differ in at the most subfiles, and aim to reduce the number of bits broadcast by the server to update the caches. We design a new elegant coded transmission strategy for the server to update the caches blindly, and also identify another simple scheme that is based on MDS codes. We then derive converse bounds on the minimum cost among all linear strategies. Equipped with these results, we identify when the caching system uses a PDA of Yan et al. For two other families of PDAs--the Maddah-Ali-Niesen scheme and a scheme by Tang& Ramamoorthy and Yan et al.--we show that our new scheme has cost when the updates are sufficiently sparse, while the scheme using MDS codes has order-optimal cost when the updates are dense.

Abstract

We propose a novel scheme for improving the word recognition accuracy using word image embeddings. We use a trained text recognizer, which can predict multiple text hypothesis for a given word image. Our fusion scheme improves the recognition process by utilizing the word image and text embeddings obtained from a trained word image embedding network. We propose EmbedNet, which is trained using a triplet loss for learning a suitable embedding space where the embedding of the word image lies closer to the embedding of the corresponding text transcription. The updated embedding space thus helps in choosing the correct prediction with higher confidence. To further improve the accuracy, we propose a plug-and-play module called Confidence based Accuracy Booster (CAB). The CAB module takes in the confidence scores obtained from the text recognizer and Euclidean distances between the embeddings to generate an updated distance vector. The updated distance vector has lower distance values for the correct words and higher distance values for the incorrect words. We rigorously evaluate our proposed method systematically on a collection of books in the Hindi language. Our method achieves an absolute improvement of around 10 percent in terms of word recognition accuracy.

Abstract

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network,(CDeC-Net) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on all the publicly available benchmark datasets-ICDAR-2013, ICDAR-2017, ICDAR-2019, UNLV, Marmot, PubLayNet, and TableBank-with extensive experiments. Our solution has three important properties:(i) a single trained model CDeC-Net‡ performs well across all the popular benchmark datasets;(ii) we report excellent performances across multiple, including higher, thresholds of IoU;(iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models will be publicly released for enabling the reproducibility of the results.

Abstract

his paper presents results of Document Visual Question Answering Challenge organized as part of" Text and Documents in the Deep Learning Era" workshop, in CVPR 2020. The challenge introduces a new problem-Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer (s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.

Abstract

A Theory of Magnitude (ATOM) suggests that space, time, and quantities are processed through a generalized magnitude system. ATOM posits that task-irrelevant magnitudes interfere with the processing of task-relevant magnitudes as all the magnitudes are processed by a common system. Many behavioural and neuroimaging studies have found support in favour of a common magnitude processing system. However, it is largely unknown whether such cross-domain monotonic mapping arises from a change in accuracy of the magnitude judgments or results from changes in precision of the processing of magnitude. Therefore, in the present study, we examined whether large numerical magnitude affects temporal accuracy or temporal precision or both. In other words, whether numerical magnitudes change our temporal experience or simply bias our duration judgments. The temporal discrimination (between …

Abstract

The task of identifying emotions from a given music track has been an active pursuit in the Music Information Retrieval (MIR) community for years. Music emotion recognition has typically relied on acoustic features, social tags, and other metadata to identify and classify music emotions. The role of lyrics in music emotion recognition remains under-appreciated in spite of several studies reporting superior performance of music emotion classifiers based on features extracted from lyrics. In this study, we use the transformer-based approach model using XLNet as the base architecture which, till date, has not been used to identify emotional connotations of music based on lyrics. Our proposed approach outperforms existing methods for multiple datasets. We used a robust methodology to enhance web-crawlers' accuracy for extracting lyrics. This study has important implications in improving applications involved in playlist generation of music based on emotions in addition to improving music recommendation systems.

Abstract

Reducing electricity consumption has emerged as a key area of concern according to the National Mission of Sustainable Habitat of Government of India. Among the Indian cities, Delhi’s electricity consumption is the highest. This paper aims to evaluate the impact of UHI on electricity consumption of Delhi. The study utilizes the satellite land surface temperature (LST) data to compute the district-wise urban heat island intensity (UHII) in Delhi. The electricity consumption and LST data are used to examine the association between them. The scatter plots between percapita net electricity consumption and night-time LST of each district show strong association between them and polynomial curves best fit this association. The equations of these polynomial curves are then used to estimate the electricity consumption of each district assuming their LSTs to be equal to that of the surrounding rural strip (i.e. without UHI effect). The difference between the observed and estimated electricity consumption at observed and assumed (i.e. rural) LSTs provided the increase in electricity consumption due to UHI. The study shows that UHI formation caused an increased electricity consumption of 2600 GWh (i.e. 11.4%) annually on an average over eight districts of Delhi during the period April 2012 to March 2017.