Abstract

t Phonetic feature extraction is used in many types of speech applications. In this paper, we propose an approach for automatic detection of retroflex approximant /õ/ in a Tamil continuous speech using sonorant regions and formant structure of speech. Retroflex approximant is one of the distinctive phonetic features of Tamil speech. It occurs in V_V and V_ contexts. In the proposed approach, slopes of the formant trajectories and spectral dynamics of F2 and F3 in the region of retroflex approximant are considered as acoustic cues for detecting them in continuous speech. In this work, numerator of the group delay function-based formant extraction method is used to track formant trajectories. Based on experimental results, formants extracted using this approach produced better evidence compared to state-of-the-art formant extraction techniques for retroflex approximant detection.

Abstract

Speaker normalization is one of the crucial aspects of an Automatic speech recognition system (ASR). Speaker normalization is employed to reduce the performance drop in ASR due to speaker variabilities. Traditional speaker normalization methods are mostly linear transforms over the input data estimated per speaker, such transforms would be efficient with sufficient data. In practical scenarios, only a single utterance from the test speaker is accessible. The present study explores speaker normalization methods for end-to-end speech recognition systems that could efficiently be performed even when single utterance from the unseen speaker is available. In this work, it is hypothesized that by suitably providing information about the speaker’s identity while training an end-to-end neural network, the capability to normalize the speaker variability could be incorporated into an ASR system. The efficiency of these normalization methods depends on the representation used for unseen speakers. In this work, the identity of the training speaker is represented in two different ways viz. i) by using a one-hot speaker code, ii) a weighted combination of all the training speakers identities. The unseen speakers from the test set are represented using a weighted combination of training speakers representations. Both the approaches have reduced the word error rate (WER) by 0.6, 1.3% WSJ corpus

Abstract

In this paper, a combination of excitation source information and vocal tract system information is explored for the task of language identification (LID). The excitation source information is represented by features extracted from linear prediction (LP) residual signal called the residual cepstral coefficients (RCC). Vocal tract system information is represented by the mel frequency cepstral coefficients (MFCC). In order to incorporate additional temporal information, shifted delta cepstra (SDC) are computed. An LID system is built using SDC over both MFCC and RCC features individually and evaluated based on their equal error rate (EER). Experiments have been performed on a dataset consisting of 13 Indian languages with about 115 h for training and 30 h for testing using a deep neural network (DNN), DNN with attention (DNN-WA) and a state-ofthe-art i-vector system. DNN-WA outperforms the baseline i-vector system. An EER of 9.93 and 6.25% are achieved using RCC and MFCC features respectively. By combining evidence from both features using a late fusion mechanism, an EER of 5.76% is obtained. This result indicates the complementary nature of the excitation source information to that of the widely used vocal tract system information for the task of LID.

Abstract

A degradation in the performance of automatic speech recognition systems (ASR) is observed in mismatched training and testing conditions. One of the reasons for this degradation is due to the presence of emotions in the speech. The main objective of this work is to improve the performance of ASR in the presence of emotional conditions using prosody modification. The influence of different emotions on the prosody parameters is exploited in this work. Emotion conversion methods are employed to generate the word level non-uniform prosody modified speech. Modification factors for prosodic components such as pitch, duration and energy are used. The prosody modification is done in two ways. Firstly, emotion conversion is done at the testing stage to generate the neutral speech from the emotional speech. Secondly, the ASR is trained with the generated emotional speech from the neutral speech. In this work, the presence of emotions in speech is studied for the Telugu ASR systems. A new database of IIIT-H Telugu speech corpus is collected to build the large vocabulary neutral Telugu speech ASR system. The emotional speech samples from IITKGP-SESC Telugu corpus are used for testing it. The emotions of anger, happiness and compassion are considered during the evaluation. An improvement in the performance of ASR systems is observed in the prosody modified speech.

Abstract

The dispute of how the human brain represents conceptual knowledge has been argued in many scientific fields. Brain imaging studies have shown that the spatial patterns of neural activation in the brain are correlated with thinking about different semantic categories of words (for example, tools, animals, and buildings) or when viewing the related pictures. In this paper, we present a computational model that learns to predict the neural activation captured in functional magnetic resonance imaging (fMRI) data of test words. Unlike the models with hand-crafted features that have been used in the literature, in this paper we propose a novel approach wherein decoding models are built with features extracted from popular linguistic encodings of Word2Vec, GloVe, Meta-Embeddings in conjunction with the empirical fMRI data associated with viewing several dozen concrete nouns. We compared these models with several other models that use word features extracted from FastText, Randomly-generated features, Mitchell’s 25 features [1]. The experimental results show that the predicted fMRI images using Meta-Embeddings meet the state-of-the-art performance. Although models with features from GloVe and Word2Vec predict fMRI images similar to the state-of-the-art model, model with features from Meta-Embeddings predicts significantly better. The proposed scheme that uses popular linguistic encoding offers a simple and easy approach for semantic decoding from fMRI experiments.

Abstract

In this paper, we propose exact passive-aggressive (PA) online algorithms for learning to rank. The proposed algorithms can be used even when we have interval labels instead of actual labels for examples. The proposed algorithms solve a convex optimization problem at every trial. We find exact solution to those optimization problems to determine the updated parameters. We propose support class algorithm (SCA) which finds the active constraints using the KKT conditions of the optimization problems. These active constrains form support set which determines the set of thresholds that need to be updated. We derive update rules for PA, PA-I and PA-II. We show that the proposed algorithms maintain the ordering of the thresholds after every trial. We provide the mistake bounds of the proposed algorithms in both ideal and general settings. We also show experimentally that the proposed algorithms successfully learn accurate classifiers using interval labels as well as exact labels. Proposed algorithms also do well compared to other approaches.

Abstract

fMRI semantic category understanding using linguistic encoding models attempt to learn a forward mapping that relates stimuli to the corresponding brain activation. Classical encoding models use linear multi-variate methods to predict the brain activation (all voxels) given the stimulus. However, these methods essentially assume multiple regions as one large uniform region or several independent regions, ignoring connections among them. In this paper, we present a mixture of expertsbased model where a group of experts captures brain activity patterns related to particular regions of interest (ROI) and also show the discrimination across different experts. The model is trained word stimuli encoded as 25-dimensional feature vectors as input and the corresponding brain responses as output. Given a new word (25-dimensional feature vector), it predicts the entire brain activation as the linear combination of multiple experts’ brain activations. We argue that each expert learns a certain region of brain activations corresponding to its category of words, which solves the problem of identifying the regions with a simple encoding model. We showcase that proposed mixture of experts-based model indeed learns region-based experts to predict the brain activations with high spatial accuracy.

Abstract

Decentralized (PO) MDPs provide a rigorous framework for sequential multiagent decision making under uncertainty. However, their high computational complexity limits the practical impact. To address scalability and real-world impact, we focus on settings where a large number of agents primarily interact through complex joint-rewards that depend on their entire histories of states and actions. Such history-based rewards encapsulate the notion of events or tasks such that the team reward is given only when the joint-task is completed. Algorithmically, we contribute---1) A nonlinear programming (NLP) formulation for such event-based planning model; 2) A probabilistic inference based approach that scales much better than NLP solvers for a large number of agents; 3) A policy gradient based multiagent reinforcement learning approach that scales well even for exponential state-spaces. Our inference and RL-based advances enable us to solve a large real-world multiagent coverage problem modeling schedule coordination of agents in a real urban subway network where other approaches fail to scale.

Abstract

Traffic management during emergency evacuation throws up a different set of challenges than a regular traffic management. We focus here on one particular challenge, namely prioritized routing. Prioritized routing may need to happen even during normal times but stands out during emergencies, since emergency vehicles, police vehicles and vehicles (such as buses) that carry a lot more people may need to have a higher priority in terms of evacuation. It is also reasonable to assume that traffic police may need to perform a centralized control of traffic since they typically have a global view of the emergency and possibly have accurate real-time updates. We therefore make the following contributions in this paper: (a) We map the prioritized routing problem to the minimum-cost maximum-flow problem, a standard problem formulation in network flow theory. (b) We then develop the Prioritized Routing Assistant for Flow …

Abstract

Handwriting recognition (HWR) in Indicscripts, like Devanagari is very challenging due to thesubtleties in the scripts, variations in rendering and the cur-sive nature of the handwriting. Lack of public handwritingdatasets in Indic scripts has long stymied the development ofoffline handwritten word recognizers and made comparisonacross different methods a tedious task in the field. Inthis paper, we release a new handwritten word dataset forDevanagari, IIIT-HW-Dev to alleviate some of these issues.We benchmark the IIIT-HW-Dev dataset using a CNN-RNN hybrid architecture. Furthermore, using this architec-ture, we empirically show that usage of synthetic data andcross lingual transfer learning helps alleviate the issue of lackof training data. We use this proposed pipeline on a publicdataset, RoyDB and achieve state of the art results.