Abstract

The presented work aims at generating a systematically annotated corpus that can support the enhancement of sentiment analysis tasks in Telugu using wordlevel sentiment annotations. From OntoSenseNet, we extracted 11,000 adjectives, 253 adverbs, 8483 verbs and sentiment annotation is being done by language experts. We discuss the methodology followed for the polarity annotations and validate the developed resource. This work aims at developing a benchmark corpus, as an extension to SentiWordNet, and baseline accuracy for a model where lexeme annotations are applied for sentiment predictions. The fundamental aim of this paper is to validate and study the possibility of utilizing machine learning algorithms, word-level sentiment annotations in the task of automated sentiment identification. Furthermore, accuracy is improved by annotating the bi-grams extracted from the target corpus.

Abstract

This paper illustrates the interface of the tool we developed for crowd sourcing and we explain the annotation procedure in detail. Our tool is named as ‘Parupalli Padajaalam1 ’ which means web of words by Parupalli. The aim of this tool is to populate the OntoSenseNet, sentiment polarity annotated Telugu resource. Recent works have shown the importance of word-level annotations on sentiment analysis. With this as basis, we aim to analyze the importance of sense-annotations obtained from OntoSenseNet in performing the task of sentiment analysis. We explain the features extracted from OntoSenseNet (Telugu). Furthermore we compute and explain the adverbial class distribution of verbs in OntoSenseNet. This task is known to aid in disambiguating wordsenses which helps in enhancing the performance of word-sense disambiguation (WSD) task(s).

Abstract

Since the beginning of the 20th century, people have started studying the correlation between language and culture. They observed how language is used in discourses to establish power relations in the society. Eggins (2004) found that the link between language and the choice made by the speaker in the exchange enable us to see speakers making meaning about interpersonal: the extent of their intimacy, their level of familiarity with each other and their attitudes and judgments. In political speeches, the speaker uses language to persuade the voters, influence their perceptions and build a positive interpersonal identity. Keeping in mind this result-oriented attempt by the speakers, Van Dijk and others (1997) describe discourse as political when it has a direct functional role as a form of political action in the political process. In this paper, we will look at four such speeches given by notable politicians from both winning and losing parties during the campaign of Andhra Pradesh State Assembly elections of 2014 and closely observe the linguistic choices made at the lexical and semantic levels. By a contrastive analysis of the speeches of winning and losing parties, we can identify the linguistic features which contribute to the outcome.

Abstract

Sentence Classification is one of the most fundamental tasks in NLP, where the aim is to classify a given sentence into a pre-defined set of classes. A lot of work has been done in English in the last few years, which vary in their methodologies. A huge proportion of these works represent the input sentences as a sequence of words in their models. Only a few of them rely on character level representation. Through this work, we introduce a new method for representing a sentence - as a sequence of syllables. As we show in this work, syllables are a better choice to represent the sub-word level information in a sentence, which is essential for morphologically rich languages. We consider the tasks of Sentiment Analysis and Question Classification in three languages showing varied morphological richness - English, Hindi and Telugu. Through extensive evaluation, we show that syllables are the best performing input type when compared to words or characters for the morphologically rich languages - Hindi and Telugu.

Abstract

India being a multilingual society, a multilingual automatic speech recognition system (ASR) is widely appreciated. Despite different orthographies, Indian languages share same phonetic space. To exploit this property, a joint acoustic model has been trained for developing multilingual ASR system using a common phone-set. Three Indian languages namely Telugu, Tamil and, Gujarati are considered for the study. This work studies the amenability of two different acoustic modeling approaches for training a joint acoustic model using common phone-set. Sub-space Gaussian mixture models (SGMM), and recurrent neural networks (RNN) trained with connectionst temporal classification (CTC) objective function are explored for training joint acoustic models. From the experimental results, it can be observed that the joint acoustic models trained with RNN-CTC have performed better than SGMM system even on 120 hours of data (approx 40 hrs per language). The joint acoustic model trained with RNN-CTC has performed better than monolingual models, due to an efficient data sharing across the languages. Conditioning the joint model with language identity had a minimal advantage. Sub-sampling the features by a factor of 2 while training RNN-CTC models has reduced the training times and has performed better. Index Terms: Speech recognition, Joint acoustic model, lowresource, common phone set, Indian languages, RNN-CTC, SGMM

Abstract

Language identification (LID) systems, which can model highlevel information such as phonotactics have exhibited superior performance. State-of-the-art models use sequential models to capture the high-level information, but these models are sensitive to the length of the utterance and do not equally generalize over variable length utterances. To effectively capture this information, a feature that can model the long-term temporal context is required. This study aims to capture the long-term temporal context by appending successive shifted delta cepstral (SDC) features. Deep neural networks have been explored for developing LID systems. Experiments have been performed using AP17-OLR database. LID systems developed by stacking SDC features have shown significant improvement compared to the system trained with SDC features. The proposed feature with residual connections in the feed-forward networks reduced the equal error rate from 21.04, 18.02, 16.45 to 14.42, 11.14 and 10.11 on the 1-second, 3-seconds and > 3-second test utterances respectively.

Abstract

This work focuses on the development of speech data comprising 23 Indian languages for developing language identification (LID) systems. Large data is a pre-requisite for developing state-of-the-art LID systems. With this motivation, the task of developing multilingual speech corpus for Indian languages has been initiated. This paper describes the composition of the data and the performances of various LID systems developed using this data. In this paper, Mel frequency cepstral feature representation is used for language identification. In this work, various state-of-the-art LID systems are developed using i-vectors, deep neural network (DNN) and deep neural network with attention (DNN-WA) models. The performance of the LID system is observed in terms of the equal error rate for i-vector, DNN and DNN-WA is 17.77%, 17.95%, and 15.18% respectively. Deep neural network with attention model shows a better performance over i-vector and DNN models

Abstract

In this study, the acoustic-phonetic attributes of palatalization in the Kashmiri speech is investigated. It is a unique phonetic feature of Kashmiri in the Indian context. An automated approach is proposed to detect this unique phonetic feature from the continuous Kashmiri speech. The i-matra vowel has the impact of palatalizing the consonant connected to it. Therefore, these consonants investigated in synchronous with vowel regions, which are spotted using the instantaneous energy computed from the envelope-derivative of the speech signal. The resonating characteristics of the vocal-tract system framework that reflect the formant dynamics are used to differentiate palatalized consonants from the other consonants. In this regard, the Hilbert envelope of the numerator of the group-delay function that provides good time-frequency resolution used to extract formants. The palatalization detection experimentation carried out in various vowel contexts using the acoustic cues, and it produced a promising result with a detection accuracy of 92.46 %.

Abstract

Automatic language identification (LID) in practical environments is gaining a lot of scientific attention due to rapid developments in multilingual speech processing applications. When an LID is operated in noisy environments a degradation in the performance can be observed and it can be majorly attributed to mismatch between the training and operating environments. This work is aimed towards developing an LID system that can robustly operate in clean and noisy environments. Traditionally, to reduce the mismatch between training and operating environments, noise is synthetically induced to the training corpus and these models are termed as multi-SNR models. In this work, various curriculum learning strategies are explored to train multi-SNR models, such that the trained models have better generalization in performance over varying background environments. I-vector, Deep neural networks (DNN) and DNN With Attention (DNN-WA) architectures are used in this work for developing LID systems. Experimental verification of the proposed approach is carried out using IIIT-H Indian database and AP17-OLR database. The performance of LID system is tested at different signal-to-noise ratio (SNR) levels using white and vehicular noises from NOISEX dataset. In comparison to multi-SNR models, the LID systems trained with curriculum learning have performed better in terms of equal error rate (EER) and generalization in EER across varying background environments. The degradation in the performance of LID systems due to environmental noise has been effectively reduced by training multi-SNR models using curriculum learning.

Abstract

Vowels are produced with an open configuration of the vocal tract, without any audible friction. The acoustic signal is relatively loud with varying strength of impulselike excitation. Vowels possess significant energy content in the low-frequency bands of the speech signal. Acoustic events such as vowel onset point (VOP) and vowel end-point (VEP) can be used as landmarks to detect vowel regions in a speech signal. In this paper, two-stage algorithm is proposed to detect precise vowel regions. In the first level, the speech signal is processed using zero frequency filtering to emphasize energy content in low-frequency bands of speech. Zero frequency filtered signal predominantly contains lowfrequency content of the speech signal as it is filtered around 0 Hz. This process is followed by the extraction of dominant spectral peaks from the magnitude spectrum around glottal closure regions of the speech signal. The vowel onset points and vowel end-points are obtained by convolving the enhanced spectral contour of zero frequency filtered signal with first order Gaussian differentiator. In the next level, a post-processing is carried out in the regions around VOP and VEP to remove spurious vowel regions based on uniformity of epoch intervals. In addition, the positions of VOPs and VEPs are also corrected using the strength of the excitation of the speech signal. The performance of the proposed vowel region detection method is compared with the existing state of art methods on TIMIT acoustic-phonetic speech corpus. It is reported that this method produced significant improvement in vowel region detection in clean and noisy environments.