Vikramjit Mitra

Text classification: A least square support vector machine approach

This paper presents a least square support vector machine (LS-SVM) that performs text classification of noisy document titles according to different predetermined categories. The systems potential is demonstrated with a corpus of 91,229 words from University of Denvers Penrose Library catalogue. The classification accuracy of the proposed LS-SVM based system is found to be over 99.9%. The final classifier is an LS-SVM array with Gaussian radial basis function (GRBF) kernel, which uses the coefficients generated by the latent semantic indexing algorithm for classification of the text titles. These coefficients are also used to generate the confidence factors for the inference engine that present the final decision of the entire classifier. The system is also compared with a K-nearest neighbor (KNN) and Naive Bayes (NB) classifier and the comparison clearly claims that the proposed LS-SVM based architecture outperforms the KNN and NB based system. The comparison between the conventional linear SVM based classifiers and neural network based classifying agents shows that the LS-SVM with LSI based classifying agents improves text categorization performance significantly and holds a lot of potential for developing robust learning based agents for text classification.

Normalized amplitude modulation features for large vocabulary noise-robust speech recognition

Background noise and channel degradations seriously constrain the performance of state-of-the-art speech recognition systems. Studies comparing human speech recognition performance with automatic speech recognition systems indicate that the human auditory system is highly robust against background noise and channel variabilities compared to automated systems. A traditional way to add robustness to a speech recognition system is to construct a robust feature set for the speech recognition model. In this work, we present an amplitude modulation feature derived from Teagers nonlinear energy operator that is power normalized and cosine transformed to produce normalized modulation cepstral coefficient (NMCC) features. The proposed NMCC features are compared with respect to state-of-the-art noise-robust features in Aurora-2 and a renoised Wall Street Journal (WSJ) corpus. The WSJ word-recognition experiments were performed on both a clean and artificially renoised WSJ corpus using SRIs DECIPHER large vocabulary speech recognition system. The experiments were performed under three train-test conditions: (a) matched, (b) mismatched, and (c) multi-conditioned. The Aurora-2 digit recognition task was performed using the standard HTK recognizer distributed with Aurora-2. Our results indicate that the proposed NMCC features demonstrated noise robustness in almost all the training-test conditions of renoised WSJ data and also improved digit recognition accuracies for Aurora-2 compared to the MFCCs and state-of-the-art noise-robust features.

Lidar detection of underwater objects using a neuro-SVM-based architecture

This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency noise. As the Lidar shots are taken from above the earth surface, it has some air backscatter information, which is of no importance for detecting underwater objects. Because of these, the air backscatter information is eliminated from the data and a segment of this data is subsequently selected to extract features for classification. This is then encoded using linear predictive coding (LPC) and polynomial approximation. The coefficients thus generated are used as inputs to the two branches of a parallel neural architecture. The decisions obtained from the two branches are vector multiplied and the result is fed to an SVM-based IE that presents the final inference. Two parallel neural architectures using multilayer perception (MLP) and hybrid radial basis function (HRBF) are considered in this paper. The proposed structure fits the Lidar data classification task well due to the inherent classification efficiency of neural networks and accurate decision-making capability of SVM. A Bayesian classifier and a quadratic classifier were considered for the Lidar data classification task but they failed to offer high prediction accuracy. Furthermore, a single-layered artificial neural network (ANN) classifier was also considered and it failed to offer good accuracy. The parallel ANN architecture proposed in this paper offers high prediction accuracy (98.9%) and is found to be the most suitable architecture for the proposed task of Lidar data classification

Articulatory Information for Noise Robust Speech Recognition

Prior research has shown that articulatory information, if extracted properly from the speech signal, can improve the performance of automatic speech recognition systems. However, such information is not readily available in the signal. The challenge posed by the estimation of articulatory information from speech acoustics has led to a new line of research known as “acoustic-to-articulatory inversion” or “speech-inversion.” While most of the research in this area has focused on estimating articulatory information more accurately, few have explored ways to apply this information in speech recognition tasks. In this paper, we first estimated articulatory information in the form of vocal tract constriction variables (abbreviated as TVs) from the Aurora-2 speech corpus using a neural network based speech-inversion model. Word recognition tasks were then performed for both noisy and clean speech using articulatory information in conjunction with traditional acoustic features. Our results indicate that incorporating TVs can significantly improve word recognition rates when used in conjunction with traditional acoustic features.

Retrieving Tract Variables From Acoustics: A Comparison of Different Machine Learning Strategies

Many different studies have claimed that articulatory information can be used to improve the performance of automatic speech recognition systems. Unfortunately, such articulatory information is not readily available in typical speaker-listener situations. Consequently, such information has to be estimated from the acoustic signal in a process which is usually termed “speech-inversion.” This study aims to propose and compare various machine learning strategies for speech inversion: Trajectory mixture density networks (TMDNs), feedforward artificial neural networks (FF-ANN), support vector regression (SVR), autoregressive artificial neural network (AR-ANN), and distal supervised learning (DSL). Further, using a database generated by the Haskins Laboratories speech production model, we test the claim that information regarding constrictions produced by the distinct organs of the vocal tract (vocal tract variables) is superior to flesh-point information (articulatory pellet trajectories) for the inversion process.

The MERL/SRI system for the 3RD CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition

This paper introduces the MERL/SRI system designed for the 3rd CHiME speech separation and recognition challenge (CHiME-3). Our proposed system takes advantage of recurrent neural networks (RNNs) throughout the model from the front speech enhancement to the language modeling. Two different types of beamforming are used to combine multi-microphone signals to obtain a single higher quality signal. Beamformed signal is further processed by a single-channel bi-directional long short-term memory (LSTM) enhancement network which is used to extract stacked mel-frequency cepstral coefficients (MFCC) features. In addition, two proposed noise-robust feature extraction methods are used with the beamformed signal. The features are used for decoding in speech recognition systems with deep neural network (DNN) based acoustic models and large-scale RNN language models to achieve high recognition accuracy in noisy environments. Our training methodology includes data augmentation and speaker adaptive training, whereas at test time model combination is used to improve generalization. Results on the CHiME-3 benchmark show that the full cadre of techniques substantially reduced the word error rate (WER). Combining hypotheses from different robust-feature systems ultimately achieved 9.10% WER for the real test data, a 72.4% reduction relative to the baseline of 32.99% WER.

Medium-duration modulation cepstral feature for robust speech recognition

Studies have shown that the performance of state-of-the-art automatic speech recognition (ASR) systems significantly deteriorate with increased noise levels and channel degradations, when compared to human speech recognition capability. Traditionally, noise-robust acoustic features are deployed to improve speech recognition performance under varying background conditions to compensate for the performance degradations. In this paper, we present the Modulation of Medium Duration Speech Amplitude (MMeDuSA) feature, which is a composite feature capturing subband speech modulations and a summary modulation. We analyze MMeDuSAs speech recognition performance using SRI Internationals DECIPHER® large vocabulary continuous speech recognition (LVCSR) system, on noise and channel degraded Levantine Arabic speech distributed through the Defense Advance Research Projects Agency (DARPA) Robust Automatic Speech Transcription (RATS) program. We also analyzed MMeDuSAs performance against the Aurora-4 noise-and-channel degraded English corpus. Our results from all these experiments suggest that the proposed MMeDuSA feature improved recognition performance under both noisy and channel degraded conditions in almost all the recognition tasks.

The SRI AVEC-2014 Evaluation System

Though depression is a common mental health problem with significant impact on human society, it often goes undetected. We explore a diverse set of features based only on spoken audio to understand which features correlate with self-reported depression scores according to the Beck depression rating scale. These features, many of which are novel for this task, include (1) estimated articulatory trajectories during speech production, (2) acoustic characteristics, (3) acoustic-phonetic characteristics and (4) prosodic features. Features are modeled using a variety of approaches, including support vector regression, a Gaussian backend and decision trees. We report results on the AVEC-2014 depression dataset and find that individual systems range from 9.18 to 11.87 in root mean squared error (RMSE), and from 7.68 to 9.99 in mean absolute error (MAE). Initial fusion brings further improvement; fusion and feature selection work is still in progress.

Highly accurate phonetic segmentation using boundary correction models and system fusion

Accurate phone-level segmentation of speech remains an important task for many subfields of speech research. We investigate techniques for boosting the accuracy of automatic phonetic segmentation based on HMM acoustic-phonetic models. In prior work [25] we were able to improve on state-of-the-art alignment accuracy by employing special phone boundary HMM models, trained on phonetically segmented training data, in conjunction with a simple boundary-time correction model. Here we present further improved results by using more powerful statistical models for boundary correction that are conditioned on phonetic context and duration features. Furthermore, we find that combining multiple acoustic front-ends gives additional gains in accuracy, and that conditioning the combiner on phonetic context and side information helps. Overall, we reduce segmentation errors on the TIMIT corpus by almost one half, from 93.9% to 96.8% boundary accuracy with a 20-ms tolerance.

From acoustics to Vocal Tract time functions

In this paper we present a technique for obtaining Vocal Tract (VT) time functions from the acoustic speech signal. Knowledge-based Acoustic Parameters (APs) are extracted from the speech signal and a pertinent subset is used to obtain the mapping between them and the VT time functions. Eight different vocal tract constriction variables consisting of five constriction degree variables, lip aperture (LA), tongue body (TBCD), tongue tip (TTCD), velum (VEL), and glottis (GLO); and three constriction location variables, lip protrusion (LP), tongue tip (TTCL), tongue body (TBCL) were considered in this study. The TAsk Dynamics Application model (TADA [1]) is used to create a synthetic speech dataset along with its corresponding VT time functions. We explore Support Vector Regression (SVR) followed by Kalman smoothing to achieve mapping between the APs and the VT time functions.