Abstract

Recent developments in deep learning methods have greatly influenced the performances of speech recognition systems. In a Hidden Markov model-Deep neural network (HMM-DNN) based speech recognition system, DNNs have been employed to model senones (context dependent states of HMM),where HMMs capture the temporal relations among senones. Due to the use of more deeper networks significant improvement in the performances has been observed and developing deep learning methods to train more deeper architectures has gained a lot of scientific interest. Optimizing a deeper network is more complex ask than to optimize a less deeper network, but recently residual network have exhibited a capability to train a very deep neural network architectures and are not prone to vanishing/exploding gradient problems. In this work, the effectiveness of residual networks have been explored for of speech recognition. Along with the depth of the residual network, the criticality of width of the residual network has also been studied. It has been observe dthat at higher depth, width of the networks is also a crucial parameter for attaining significant improvements. A 14-hoursubset of WSJ corpus is used for training the speech recognition systems, it has been observed that the residual networks have shown much ease in convergence even with a depth much higher than the deep neural network. In this work, using residual networks an absolute reduction of 0.4 in WER error rates (8%reduction in the relative error) is attained compared to the best performing deep neural network.

Abstract

Significant developments in deep learning methods have been achieved with the capability to train more deeper networks. The performance of speech recognition system has been greatly improved by the use of deep learning techniques. Most of the developments in deep learning are associated with the development of new activation functions and the corresponding initializations. The development of Rectified linear units (ReLU)has revolutionized the use of supervised deep learning methods for speech recognition. Recently there has been a great deal of research interest in the development of activation functionsLeaky-ReLU (LReLU), Parametric-ReLU (PReLU), Exponentia lLinear units (ELU) and Parametric-ELU (PELU). This work isaimed at studying the influence of various activation functions onspeech recognition system. In this work, a hidden Markov model-Deep neural network (HMM-DNN) based speech recognitionis used, where deep neural networks with different activationfunctions have been employed to obtain the emission probabilitiesof hidden Markov model. In this work, two datasets i.e., TIMITand WSJ are employed to study the behavior of various speechrecognition systems with different sized datasets. During thestudy, it is observed that the performance of ReLU-networksis superior compared to the other networks for the smaller sizeddataset (i.e., TIMIT dataset). For the datasets of sufficientlylarger size (i.e., WSJ) performance of ELU-networks is superiorto the other networks.

Abstract

Sampark is machine translation system providing translations among nine pairs of Indian languages. Machine translation system is a class of natural language processing applications that is far more complex and highly compute intensive in nature. As the load on the deployed system increases, optimization becomes a challenge. Caching is one of the available options to improve the performance of a software system with increasing load which exhibit the characteristics of locality of reference. Sampark MT system being a natural language processing application exhibits this characteristic.Memcachedis a well-known, simple, in-memory caching solution that has been applied to improve the performance of several distributed web applications in the past. This paper describes how memcached has been applied to improve the performance of Sampark machine translation service which is deployed on a large cluster of machines. By applying distributed caching to MT system the performance of the system has improved upto 40%

Abstract

In this paper, deep neural networks (DNN) are applied for acoustic scene classification task provided by DCASE2017 challenge. We perform experiment on a dataset consisting of 15 types of acoustic scenes with a given total development data and evolution data of task1. We propose an DNN architecture for utterance level classification. Evaluation of models were performed on given evolution data of task1 for 4 folds using development data. In this approach MFCC and IMFCC feature vectors are used to train DNN model and their DNN scores were combined to test the system. On the official development data set of the task1 challenge, an accuracy of 81.28% is achieved.

Abstract

This paper investigates the application of unsupervised acoustic unit discovery for topic identification (topic ID) of spoken audio documents. The acoustic unit discovery method is based on a non-parametric Bayesian phone-loop model that segments a speech utterance into phone-like categories. The discovered phone-like (acoustic) units are further fed into the conventional topic ID framework. Using multilingual bottleneck features for the acoustic unit discovery, we show that the proposed method outperforms other systems that are based on cross-lingual phoneme recognizer.

Abstract

Bursts are produced by closing the oral tract at a place of articulation and suddenly releasing the acoustic energy built-up behind the closure in the tract. The release of energy is an impulselike behavior, and it is followed by a short duration of frication. The burst release is short and mostly weak in nature (compared to sonorant sounds), thus making it difficult to detect its presence in continuous speech. This paper attempts to identify burst onsets based on parameters derived from single frequency filtering (SFF) analysis of speech signals. The SFF envelope and phase information give good spectral and temporal resolutions of certain features of the signal. Signal reconstructed from the SFF phase information is shown to be useful in locating burst onsets. Entropy and spectral distance parameters from the SFF spectral envelopes are used to refine the burst onset candidate set. The identified burst onset locations are compared with manual annotations in the TIMIT database.

Abstract

Automatic speaker verification systems are more vulnerable to spoofing attacks. Recently, various countermeasures have been developed for detecting high technology attacks such as speech synthesis and voice conversion. However, there is a wide gap in dealing with replay attacks. In this paper, we propose a new feature for replay attack detection based on single frequency filtering (SFF), which provides high temporal and spectral resolution at each instant. Single frequency filtering cepstral coefficients (SFFCC) with Gaussian mixture model classifier is used for the experimentation on the standard BTAS-2016 corpus. The previously reported best result, which is based on constant Q cepstral coefficients (CQCC) has achieved a half total error rate of 0.67% on this data-set. Our proposed method outperforms the state of the art (CQCC) with a half total error rate of 0.0002%.

Abstract

We describe the system submitted to IBEREVAL-2017 for stance and gender detection in tweets on Catalan Independence [1]. We developed a supervised system using Support Vector Machines with radial basis function kernel to identify the stance and gender of the tweeter using various character level and word level features. Our system achieves a macro-average of F-score(FAVOR) and F-score(AGAINST) of 0.46 for stance detection in both Spanish and Catalan and an accuracy of 64.85% and 44.59% for Gender detection in Spanish and Catalan respectively.

Abstract

The ASVspoof 2017 challenge is about the detection of replayed speech from human speech. The proposed system makes use of the fact that when the speech signals are replayed, they pass through multiple channels as opposed to original recordings. This channel information is typically embedded in low signal to noise ratio regions. A speech signal processing method with high spectro-temporal resolution is required to extract robust features from such regions. The single frequency filtering (SFF) is one such technique, which we propose to use for replay attack detection. While SFF based feature representation was used at front-end, Gaussian mixture model and bi-directional long short-term memory models are investigated at the backend as classifiers. The experimental results on ASVspoof 2017 dataset reveal that, SFF based representation is very effective in detecting replay attacks. The score level fusion of back end classifiers further improved the performance of the system which indicates that both classifiers capture complimentary information

Abstract

We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar (Chomsky, 1965), we mitigate the sampling bias by generating all theoretically possible alternative word orders of a clause from the existing (kernel) structures in the treebank. Training our parser on canonical and transformed structures improves performance on conversational data by around 9% LAS over the baseline newswire parser.