Abstract

Epochs are the abrupt-closure events in vocal fold vibration during the production of voiced speech. Zero frequency filtering is a simple and effective technique used to estimate the glottal closure instants accurately from the speech signal. However, the zero frequency filter is an unstable system. Hence, it may not be suitable for practical implementation due to the requirements of high precision computation. In this letter, zero-phase zero frequency resonator is proposed as an alternative to zero frequency filter. The proposed approach provides a stable zero-phase response. The experimental results indicate that the performance of the proposed method outperformed the state-of-the-art methods in terms of identification rate 99.17% and provides comparable performance in terms of false alarm rate (0.41%), and identification accuracy (0.28 ms).

Abstract

Self-attention networks are being popularly employed in sequence classification and sequence summarization tasks. State-of-the-art models use sequential models to capture the high-level information, but these models are sensitive to length of utterance and do not equally generalize over variable length utterances. This work explores to study the efficiency of recent advancements in self-attentive networks for improving the performance of the LID system. In self-attentive network, variable length input sequence is converted to fixed dimensional vector which represents the whole sequence. The weighted mean of input sequence is considered as utterance level representation. Along with the mean, a standard deviation is employed to represent the whole input sequence. Experiments are performed using AP17-OLR database. Use of mean with standard deviation has reduced the equal error rate (EER) with an 8% relative improvement. A multi-head attention mechanism is introduced in self-attention networks with an assumption that each head captures the distinct information to discriminate languages. Use of multi-head self-attention has further reduced the EER with a 13% relative improvement. Best performance is achieved with multi-head self-attention network with residual connections. Shifted delta cepstral features (SDC) and stacked SDC features are used for developing LID systems.

Abstract

—India is a multilingual society having more than 1600 languages. Most of these languages are having an overlapping set of phonemes. This makes developing language identification (LID) framework difficult for Indian languages. In this paper, the above challenge is addressed using phonetic features. To model the temporal variations in phonetic features, attention based residual-time delay neural network (RES-TDNN) is proposed. This network effectively captures long-range temporal dependencies through TDNN and attention mechanism. The proposed network has been evaluated on IIITH-ILSC database using phonetic and acoustic features. The database consists of 22 official Indian languages and Indian English. Attention based RES-TDNN outperformed the other state-of-the-art networks such as deep neural network, long short-term memory network and produced an equal error rate of 9.46%. Further, the fusion of shifted delta cepstral and phonetic features have improved the performance.

Abstract

—India is a multilingual society having more than 1600 languages. Most of these languages are having an overlapping set of phonemes. This makes developing language identification (LID) framework difficult for Indian languages. In this paper, the above challenge is addressed using phonetic features. To model the temporal variations in phonetic features, attention based residual-time delay neural network (RES-TDNN) is proposed. This network effectively captures long-range temporal dependencies through TDNN and attention mechanism. The proposed network has been evaluated on IIITH-ILSC database using phonetic and acoustic features. The database consists of 22 official Indian languages and Indian English. Attention based RES-TDNN outperformed the other state-of-the-art networks such as deep neural network, long short-term memory network and produced an equal error rate of 9.46%. Further, the fusion of shifted delta cepstral and phonetic features have improved the performance.

Abstract

In this paper, phonetic features derived from the joint acoustic model (JAM) of a multilingual end to end automatic speech recognition system are proposed for Indian language identification (LID). These features utilize contextual information learned by the JAM through long short-term memoryconnectionist temporal classification (LSTM-CTC) framework. Hence, these features are referred to as CTC features. A multi-head self-attention network is trained using these features, which aggregates the frame-level features by selecting prominent frames through a parametrized attention layer. The proposed features have been tested on IIITH-ILSC database that consists of 22 official Indian languages and Indian English. Experimental results demonstrate that CTC features outperformed i-vector and phonetic temporal neural LID systems and produced an 8.70% equal error rate. The fusion of shifted delta cepstral and CTC feature-based LID systems at the model level and feature level further improved the performance.

Abstract

Decentralized MDPs (Dec-MDPs) provide a rigorous framework for collaborative multi-agent sequential decisionmaking under uncertainty. However, their computational complexity limits the practical impact. To address this, we focus on a class of Dec-MDPs consisting of independent collaborating agents that are tied together through a global reward function that depends upon their entire histories of states and actions to accomplish joint tasks. To overcome scalability barrier, our main contributions are:(a) We propose a new actor-critic based Reinforcement Learning (RL) approach for event-based Dec-MDPs using successor features (SF) which is a value function representation that decouples the dynamics of the environment from the rewards;(b) We then present Dec-ESR (Decentralized Event based Successor Representation) which generalizes learning for event-based Dec-MDPs using SF within an end-to-end deep RL framework;(c) We also show that Dec-ESR allows useful transfer of information on related but different tasks, hence bootstraps the learning for faster convergence on new tasks;(d) For validation purposes, we test our approach on a large multi-agent coverage problem which models schedule coordination of agents in a real urban subway network and achieves better quality solutions than previous best approaches.

Abstract

One of the major drawbacks of RL is the low sample efficiency of the learning algorithms. In many cases domain expertise can help to mitigate this effect. Teacher-Student framework is one such paradigm, where a more experienced agent (teacher) upon being queried helps to accelerate the student’s learning by providing advice on the action to take in a given state. Real world teachers not only provide the action to take in a given state but also provide a more informative signal using the synthesis of knowledge they may have gained with experience. With this motivation, we propose a richer advising framework where the teacher augments the student’s knowledge by also providing the expected long term reward of following that action. The student can then use this value to steadily guide its Q-Network in the correct direction which can lead to a quicker convergence. To help student relive the advices received throughout its learning, we introduce an additional memory called the Advice Replay Memory (ARM). Results show that a student following our approach (a) is able to exploit the environment better, and (b) has a steeper learning curve.

Abstract

This paper describes the Neural Machine Translation systems used by IIIT Hyderabad (CVIT-MT) for the translation tasks part of WAT-2019. We participated in tasks pertaining to Indian languages and submitted results for English-Hindi, Hindi-English, English-Tamil and Tamil-English language pairs. We employ Transformer architecture experimenting with multilingual models and methods for low-resource languages.

Abstract

Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinese characters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4. The official website for the competition is http://rrc.cvc.uab.es/?ch=12.

Abstract

In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of annotation often limits the quantity of labels available for training in any domain, while deployment is easier if a single model works well across domains. In this paper, we pose the novel problem of universal semi-supervised semantic segmentation and propose a solution framework, to meet the dual needs of lower annotation and deployment costs. In contrast to counterpoints such as fine tuning, joint training or unsupervised domain adaptation, universal semi-supervised segmentation ensures that across all domains: (i) a single model is deployed, (ii) unlabeled data is used, (iii) performance is improved, (iv) only a few labels are needed and (v) label spaces may differ. To address this, we minimizesupervised as well as within and cross-domain unsupervised losses, introducing a novel feature alignment objective based on pixel-aware entropy regularization for the latter. We demonstrate quantitative advantages over other approaches on several combinations of segmentation datasets across different geographies (Germany, England, India) and environments (outdoors, indoors), as well as qualitative insights on the aligned representations.