Tanmay Bhowmik

On Embedding of Text in Audio A Case of Steganography

A steganographic method of embedding textual information in an audio file is presented in this paper. In the proposed technique, first the audio file is sampled and then an appropriate bit of each alternate sample is altered to embed the textual information. As a steganographic approach the perceptual quality of the host audio signal was not to be degraded.

Detection of attributes for Bengali phoneme in continuous speech using deep neural network

Hidden Markov Model (HMM) has contributed greatly in the area of speech recognition during last two decades. However, in recent days, detection-based, bottom-up speech recognition techniques achieve high success rate. In this detection-based, bottom-up approach of speech recognition, first step is detection of speech attributes like place and manner of articulation of the phonemes. This paper describes about the detection of attributes which leads to identification of place and manner of articulation of Bengali phonemes using Deep Neural Network (DNN).

Deep neural network based phonological feature extraction for Bengali continuous speech

Automatic Speech Attribute Transcription framework is a recently proposed paradigm for detection based bottom-up speech recognition. Speech signal contains a large set of related information, known as speech attributes that include a set of fundamental speech sound with their linguistic identification that is phonological features. In this study, a bank of Deep Neural Network based attribute detectors has been applied to Bengali continuous speech corpus to detect phonological features of Bengali language. 89.17% of average attribute detection accuracy was achieved for Bengali continuous speech. This experiment was repeated using TIMIT speech corpus to ensure the system robustness, and the average detection accuracy was 89.40%.

Manner of articulation based Bengali phoneme classification

A phoneme classification model has been developed for Bengali continuous speech in this experiment. The analysis was conducted using a deep neural network based classification model. In the first phase, phoneme classification task has been performed using the deep-structured classification model along with two baseline models. The deep-structured model provided better overall classification accuracy than the baseline systems which were designed using hidden Markov model and multilayer Perceptron respectively. The confusion matrix of all the Bengali phonemes generated by the classification model is observed, and the phonemes are divided into nine groups. These nine groups provided better overall classification accuracy of 98.7%. In the next phase of this study, the place and manner of articulation based phonological features are detected and classified. The phonemes are regrouped into 15 groups using the manner of articulation based knowledge, and the deep-structured model is retrained. The system provided 98.9% of overall classification accuracy this time. This is almost equal to the overall classification accuracy which was observed for nine phoneme groups. But as the nine phoneme groups are redivided into 15 groups, the phoneme confusion in a single group became less which leads to a better phoneme classification model.

Detection and classification of place and manner of articulation for Bengali continuous speech

In this paper the place and manner of articulation based phonological features are detected and classified. Deep Neural Network based model has been used for detection and classification task. The deep structured model is pre-trained by stacked denoising autoencoder. The system obtained 89.17% overall accuracy in detection task. In case of classification task, 50.2% of classification accuracy is observed for classifying the place of articulation based features. The manner of articulation is divided into 15 groups based on some manner based knowledge combination and classification task is performed to achieve 98.9% of classification accuracy.

Deep Neural Network Based Recognition and Classification of Bengali Phonemes: A Case Study of Bengali Unconstrained Speech

This paper proposed a phoneme recognition and classification model for Bengali continuous speech. A Deep Neural Network based model has been developed for the recognition and classification task where the Stacked Denoising Autoencoder is used to generatively pre-train the deep network. Autoencoders are stacked to form the deep-structured network. Mel-frequency cepstral coefficients are used as input data vector. In hidden layer, 200 numbers of hidden units have been utilized. The number of hidden layers of the deep network is kept as three. The phoneme posterior probability has been derived in the output layer. This proposed model has been trained and tested using unconstrained Bengali continuous speech data collected from the different sources (TV, Radio, and normal conversation in a laboratory). In recognition phase, the Phoneme Error Rate is reported for the deep-structured model as 24.62% and 26.37% respectively for the training and testing while in the classification task this model achieves 86.7% average phoneme classification accuracy in training and 82.53% in the testing phase.