Abstract

In recent years, text-to-speech (TTS) systems have shown considerable improvement as far as the quality of the synthetic speech is concerned. Data driven synthesis methods using syllable as basic unit for concatenation, have proved to generate high quality speech for Indian Languages because of their advantage of prosodic matching function. However, still there is no acceptable solution to the optimal selection of speech segments in terms of audible discontinuities and human perception. This problem gets aggravated in the cases where there is no enough data for building the voice due to the missing units. In this paper, we continue our efforts in trying to address this by investigating the use of a new continuity measure based on maximum signal correlation for optimal selection of units in concatenative text-to-speech (TTS) synthesis framework. We explore two formulations for calculating the signal correlation: cross correlation (CC) based and average magnitude difference function (AMDF) based. We first perform an initial experiment to understand the significance of the approach and then build 5 experimental systems. Evaluations on 30 sentences for each of these languages by native users of the language show that the proposed continuity measure results in more natural sounding synthesis.

Abstract

Automatic detection of vowel landmarks is useful in many applications such as automatic speech recognition (ASR), audio search, syllabification of speech and expressive speech processing. In this paper, acoustic features extracted around epochs are proposed for detection of vowel landmarks in continuous speech. These features are based on zero frequency filtering (ZFF) and single frequency filtering (SFF) analyses of speech. Excitation source based features are extracted using ZFF method and vocal tract system based features are extracted using SFF method. Based on these features, a rule-based algorithm is developed for vowel landmark detection (VLD). Performance of the proposed VLD algorithm is studied on three different databases namely, TIMIT (read), NTIMIT (channel degraded) and Switchboard corpus (conversational speech). Results show that the proposed algorithm performs equally well compared to state-of-the-art techniques on TIMIT and betteron NTIMIT and Switchboard corpora. Proposed algorithmalso displays consistent performance on TIMIT and NTIMITdatasets for different levels of noise degradations.

Abstract

In natural conversations, significant part of laughter co-occurs with speech which is referred to as speech-laugh. Hence, speech-laugh will have characteristics of both laughter and neutral speech. But it is not clearly evident how acoustic properties of neutral speech are influenced by its co-occurring laughter. The objective of this study is to analyze the acoustic variations between vowel regions of laughter, speech-laugh and neutral speech. The features based on excitation source characteristics extracted at epochs are considered in this study. Features extracted in the vowel regions of speech-laugh exhibit deviations from that of laughter and neutral speech. These deviations in feature values are exploited to discriminate speech-laugh from laughter and neutral speech. Two different datasets consisting of conversational speech and meeting recordings are used in this analysis. Experimental results show that the discrimination between the three classes obtained by considering vowel regions is better than that of considering the complete utterance.

Abstract

The present study focuses on the text-independent speaker recognition in emotional conditions. In this paper, both system and source features are considered to represent speaker specific information. At the model level, Gaussian Mixture Models (GMMs), Gaussian Mixture Model-Universal Background Model (GMM-UBM) and Deep Neural Networks (DNN) are explored. The experiments are performed using 3 emotional databases, i.e. German emotional speech database (EMO-DB), IITKGP-SESC: Hindi and IITKGP-SESC: Telugu databases. The emotions considered in the present study are neutral, anger, happy and sad. The results show that, the performance of a speaker recognition system trained with clean speech is degrading while testing with emotional data irrespective of feature used or model used to build the system. The best results are obtained for the score level fusion of system and source features based systems when speakers are modeled with DNNs.

Abstract

Due to increase of online product reviews posted daily through various modalities such as video, audio and text, sentimental analysis has gained huge attention. Recent developments in web technologies have also enabled the increase of web content in Hindi. In this paper, an approach to detect the sentiment of an online Hindi product reviews based on its multi-modality natures (audio and text) is presented. For each audio input, Mel Frequency Cepstral Coefficients (MFCC) features are extracted. These features are used to develop a sentiment models using Gaussian Mixture Models (GMM) and Deep Neural Network (DNN) classifiers. From results, it is observed that DNN classifier gives better results compare to GMM. Further textual features are extracted from the transcript of the audio input by using Doc2vec vectors. Support Vector Machine (SVM) classifier is used to develop a sentiment model using these textual features. From experimental results it is observed that combining both the audio and text features results in improvement in the performance for detecting the sentiment of an online product reviews.

Abstract

Source and system features are extensively used in building Speaker Recognition (SR) systems. In this paper, we investigate the influence of source and system features on the performance of the SR system in emotional conditions. The Linear Prediction Residual Cepstral Coefficients (LPRCC) which corresponds to source features, and Mel Frequency Cepstral Coefficients (MFCC) and Linear Prediction Cepstral Coefficients (LPCC) that correspond to system features are used for modeling SR system. A maximum-likelihood classifier based on Gaussian mixture density functions is used and experiments are carried out on 3 standard emotional speech databases (Indian Institute of Technology-Simulated Emotion speech corpus (IITKGP-SESC): Hindi, IITKGP-SESC: Telugu and German Emotional Speech Database (EMO-DB)). The speaker models are trained with neutral utterances and tested with 3 types (anger, happy and sad) of emotional speech utterances. Based on experimental results, the performance degradation was observed in mismatched (trained with one emotion and tested with other emotion) case and the average percentage of degradation in SR task using source features is approximately 16% more compared to system features. The performance degradation of SR system is nullified when trained and tested with the same emotion.

Abstract

In this paper we present our submission for FIRE 2016 Shared Task on Code Mixed Entity Extraction in Indian Languages. We describe a Neural Network system for Entity Extraction in Hindi-English Code Mixed text. Our method uses distributed word representations as features for the Neural Network and therefore, can easily be replicated across languages. Our system ranked first place forHindi-English with an F1-score of 68.24%

Abstract

Internet users today prefer getting precise answers to their questions rather than sifting through a bunch of relevant documents provided by search engines. This has led to the huge popularity of Community Question Answering (cQA) services like Yahoo! Answers, Baidu Zhidao, Quora, Stack Over flowetc., where forum users respond to questions with precise answers. Over time, such cQA archives become rich repositories of knowledge encoded in the form of questions and user generated answers. In cQA archives, retrieval of similar questions, which have already been answered in some form, is important for improving the effectiveness of such forums. The main challenge while retrieving similar questions is the “lexico-syntactic” gap between the user query and the questions already present in the forum. In this paper, we pro-pose a novel approach called “Deep Structured Topic Model (DSTM)” to bridge the lexico-syntactic gap between the question posed by the user and forum questions. DSTM employs a two-step process consisting of initially retrieving similar questions that lie in the vicinity of the query and latent topic vector space and then re-ranking them using a deep layered semantic model. Experiments on large scale real-life cQA dataset show that our approach outperforms the state-of-the-art translation and topic based baseline approaches

Abstract

It has been shown that transition-based methods can be used for syntactic word ordering and tree linearization, achieving significantly faster speed compared with traditional best-first methods. State-of-the-art transition-based models give competitive results on ab-stract word ordering and unlabeled tree lin-earization, but significantly worse results on labeled tree linearization. We demonstrate that the main cause for the performance bottle-neck is the sparsity of SHIFT transition actions rather than heavy pruning. To address this is-sue, we propose a modification to the standard transition-based feature structure, which reduces feature sparsity and allows look ahead features at a small cost to decoding efficiency.Our model gives the best reported accuracies on all benchmarks, yet still being over 30times faster compared with best-first-search.

Abstract

In this paper, we present Kathaa1, anopen source web based Visual Programming Framework for NLP applications. It supports design, execution and analysis of complex NLP systems by choosing and visually connecting NLP modules from an already avail-able and easily extensible Module library. It models NLP systems as a Directed Acyclic Graph of optionally parallalized information flow, and lets the user choose and use avail-able modules in their NLP applications irrespective of their technical proficiency. Kathaa exposes a precise Module definition API to al-low easy integration of external NLP components (along with their associated services as docker containers), it allows everyone to publish their services in a standardized format for everyone else to use it out of the box.