In this work, we focus on effectively leveraging and integrating information from concept-level as well as word-level via projecting concepts and words into a lower dimensional space while retaining most critical semantics. In a broad context of opinion understanding system, we investigate the use of the fused embedding for several core NLP tasks: named entity detection and classification, automatic speech recognition reranking, and targeted sentiment analysis.
Hidden Markov model based various phoneme recognition methods for Bengali language is reviewed. Automatic phoneme recognition for Bengali language using multilayer neural network is reviewed. Usefulness of multilayer neural network over single layer neural network is discussed. Bangla phonetic feature table construction and enhancement for Bengali speech recognition is also discussed. Comparison among these methods is discussed.
This thesis introduces the sequence to sequence model with Luong's attention mechanism for end-to-end ASR. It also describes various neural network algorithms including Batch normalization, Dropout and Residual network which constitute the convolutional attention-based seq2seq neural network. Finally the proposed model proved its effectiveness for speech recognition achieving 15.8% phoneme error rate on TIMIT dataset.
The major system is a mnemonic system that can be used to memorize sequences of numbers. In this work, we present a method to automatically generate sentences that encode a given number. We propose several encoding models and compare the most promising ones in a password memorability study. The results of the study show that a model combining part-of-speech sentence templates with an $n$-gram language model produces the most memorable password representations.
We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness to outliers is evaluated on two real-world tasks related to speech segmentation. Our algorithms outperform baseline segmentation algorithms.
We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. Our approach examines the distribution of transitions, selects the uncommon words, and makes lexicalized states for the words. We performed a part-of-speech tagging experiment on the Brown corpus to evaluate the resultant language model and discovered that this technique improved the tagging accuracy by 0.21% at the 95% level of confidence.
In this paper, we seek to reduce the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention mechanisms; then, we pre-train the transformer-based model with those attentions in a self-supervised fashion and use them as feature extractors on downstream tasks, including phoneme classification and speaker classification. We find that the proposed approach, which only uses hand-crafted and learnable attentions, is comparable with the full self-attention.
We present OpenSeq2Seq -- an open-source toolkit for training sequence-to-sequence models. The main goal of our toolkit is to allow researchers to most effectively explore different sequence-to-sequence architectures. The efficiency is achieved by fully supporting distributed and mixed-precision training. OpenSeq2Seq provides building blocks for training encoder-decoder models for neural machine translation and automatic speech recognition. We plan to extend it with other modalities in the future.
This paper presents a syntactic lexicon for English that was originally derived from the Oxford Advanced Learner's Dictionary and the Oxford Dictionary of Current Idiomatic English, and then modified and augmented by hand. There are more than 37,000 syntactic entries from all 8 parts of speech. An X-windows based tool is available for maintaining the lexicon and performing searches. C and Lisp hooks are also available so that the lexicon can be easily utilized by parsers and other programs.
While significant progress has been made using machine learning algorithms to detect hate speech, important technical challenges still remain to be solved in order to bring their performance closer to human accuracy. We investigate several of the most recent visual-linguistic Transformer architectures and propose improvements to increase their performance for this task. The proposed model outperforms the baselines by a large margin and ranks 5$^{th}$ on the leaderboard out of 3,100+ participants.
Add to Chrome
Add to Firefox