Syllable-based Myanmar language model for speech recognition

We propose a method of dynamically registering out-of-vocabulary (OOV) words by assigning the pronunciations of these words to pre-inserted OOV tokens, editing the pronunciations of the tokens. To do this, we add OOV tokens to an additional, partial copy of our corpus, either randomly or to part-of-speech (POS) tags in the selected utterances, when training the language model (LM) for speech recognition. This results in an LM containing OOV tokens, to which we can assign pronunciations. We also investigate the impact of acoustic complexity and the “natural” occurrence frequency of OOV words on the recognition of registered OOV words. The proposed OOV word registration method is evaluated using two modern automatic speech recognition (ASR) systems, Julius and Kaldi, using DNN-HMM acoustic models and N-gram language models (plus an additional evaluation using RNN re-scoring with Kaldi). Our experimental results show that when using the proposed OOV registration method, modern ASR systems can recognize OOV words without re-training the language model, that the acoustic complexity of OOV words affects OOV recognition, and that differences between the “natural” and the assigned occurrence frequencies of OOV words have little impact on the final recognition results.

In this paper, we present an empirical study that utilizes morph-syntactical information to improve translation quality. With three kinds of language pairs matched according to morph-syntactical similarity or difference, we investigate the effects of various morpho-syntactical information, such as base form, part-of-speech, and the relative positional information of a word in a statistical machine translation framework. We learn not only translation models but also word-based/class-based language models by manipulating morphological and relative positional information. And we integrate the models into a log-linear model. Experiments on multilingual translations showed that such morphological information as part-of-speech and base form are effective for improving performance in morphologically rich language pairs and that the relative positional features in a word group are useful for reordering the local word orders. Moreover, the use of a class-based n-gram language model improves performance by alleviating the data sparseness problem in a word-based language model.

Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture strict logic from free-form texts. In this paper, we propose a novel graph-based language model, Logical-GLM, to extract strict logic from free-form texts and then infuse into language models. Specifically, we first capture information from natural language instructions and construct logical probability graphs that generally describe domains. Next, we generate logical skeletons to guide language model training, infusing domain knowledge into language models. At last, we alternately optimize the searching policy of graphs and language models until convergence. The experimental results show that Logical-GLM is both effective and efficient compared with traditional language models, despite using smaller-scale training data and fewer parameters. Our approach can generate instructional texts with more correct logic owing to the internalized domain knowledge. Moreover, the search of logical graphs reflects the inner mechanism of the language models, which improves the interpretability of black-box models.

Speech-recognition systems must often decide between competing ways of breaking up the acoustic input into strings of words. Since the possible strings may be acoustically similar, a language model is required; given a word string, the model returns its linguistic probability. Several Markov language models are discussed. A novel kind of language model which reflects short-term patterns of word use by means of a cache component (analogous to cache memory in hardware terminology) is presented. The model also contains a 3g-gram component of the traditional type. The combined model and a pure 3g-gram model were tested on samples drawn from the Lancaster-Oslo/Bergen (LOB) corpus of English text. The relative performance of the two models is examined, and suggestions for the future improvements are made. >

We present a study of byte pair encoding (BPE) based language modeling for open vocabulary Latin language OCR. On a large-scale handwritten English OCR task, we demonstrate that a simple BPE-based n-gram language model (LM) can deal with out-of-vocabulary word problem effectively and achieve better accuracy-footprint tradeoff than a state-of-the-art hybrid word/subword n-gram LM interpolated by a standard hybrid LM, a word-based LM, and a subword-based LM. On another large-scale printed OCR task for six Latin languages, namely English, Spanish, French, German, Italian, and Portuguese, we discover that a unified OCR system with a single character-based optical model and a single BPE-based n-gram LM shared by six languages performs better than language-dependent OCR systems. BPE-based LM offers a good product solution for both monolingual and multilingual open-vocabulary Latin language OCR.

Recurrent neural network language models (RNNLM) have become an increasingly popular choice for state-of-the-art speech recognition systems. RNNLMs are normally trained by minimizing the cross entropy (CE) using the stochastic gradient descent (SGD) algorithm. The SGD method only uses first-order derivatives and no higher order gradient information is used to consider the correlation between model parameters. It is unable to fully capture the curvature of the error cost function. This can lead to slow convergence in model training. In this paper, a limited-memory Broyden Fletcher Goldfarb Shannon (L-BFGS) based second order optimization technique is proposed for RNNLMs. This method efficiently approximates the matrix-vector product between the inverse Hessian and gradient vector via a recursion over past gradients with a compact memory requirement. Consistent perplexity and error rate reductions are obtained over the SGD method on two speech recognition tasks: Switchboard English and Babel Cantonese. A faster convergence and speed up in RNNLM training time was also obtained. Index Terms: recurrent neural network, language model, second order optimization, limited-memory BFGS, speech recognition

Code-switching is a commonly occurring phenomenon in many multilingual communities, wherein a speaker switches between languages within a single utterance. Conventional Word Error Rate (WER) is not sufficient for measuring the performance of code-mixed languages due to ambiguities in transcription, misspellings and borrowing of words from two different writing systems. These rendering errors artificially inflate the WER of an Automated Speech Recognition (ASR) system and complicate its evaluation. Furthermore, these errors make it harder to accurately evaluate modeling errors originating from code-switched language and acoustic models. In this work, we propose the use of a new metric, transliteration-optimized Word Error Rate (toWER) that smoothes out many of these irregularities by mapping all text to one writing system and demonstrate a correlation with the amount of code-switching present in a language. We also present a novel approach to acoustic and language modeling for bilingual code-switched Indic languages using the same transliteration approach to normalize the data for three types of language models, namely, a conventional n-gram language model, a maximum entropy based language model and a Long Short Term Memory (LSTM) language model, and a state-of-the-art Connectionist Temporal Classification (CTC) acoustic model. We demonstrate the robustness of the proposed approach on several Indic languages from Google Voice Search traffic with significant gains in ASR performance up to 10% relative over the state-of-the-art baseline.

To improve the accuracy of lip-reading recognition, an emotions and topic-related mixed language model has been researched. On the basis of the key words, the topic is divided by subject words, improved scene training corpus design and parameter estimation methods are used, the scene training corpus of different topics is expressed as the fuzzy subset of the whole scene training corpus, parameter estimated which can be got is also based on the fuzzy training set of different topics. The problem of sparse data which is introduced by less of training corpus in traditional language model has been eased by improved methods, quantitative description about the relationship of scene training corpus and topics has been presented, and full use of the image identification techniques for expression recognition in lipreading recognition area, auxiliary emotional factors language model to carry out lip-reading recognition.

Although n-gram models are still the de facto standard in language modeling for speech recognition, it has been shown that more sophisticated models achieve better accuracy by taking additional information, such as syntactic rules, semantic relations or domain knowledge into account. Unfortunately, most of the effort in developing such models goes into the implementation of handcrafted inference routines. What lacks is a generic mechanism to introduce background knowledge into a language model. We propose the use of dynamic Bayesian networks for this purpose. Dynamic Bayesian networks can be seen as a generalization of the n-gram models and hmms traditionally used in language modeling and speech recognition. Whereas those models use a single random variable to represent state, Bayesian networks can have any number of variables. As such they are particularly well-suited for the construction of models that take additional information into account. In this paper language modeling with belief networks is discussed. Examples of belief network implementations of well-known language models are given and a new model is presented that models dependencies between the content words in a sentence.KeywordsBayesian NetworkSpeech RecognitionLanguage ModelContent WordDynamic Bayesian NetworkThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This work presents a 2-pass recognition method for highly inflected agglutinative languages based on an Estonian large vocabulary recognition task. Morphemes are used as basic recognition units in a standard trigram language model in the first pass. The recognized morphemes are reconstructed back to words using hidden event language model for compound word detection. In the second pass, the vocabulary from N-best sentence candidates from the first pass is used to create an adaptive sentence-specific word-based language model which is applied for rescoring the N-best hypotheses. The sentence specific language model is based on the factored language model paradigm and estimates word probabilities based on the preceding two words and part-of-speech tags. The method achieves a 7.3% relative word error rate improvement over the baseline system that is used in the first pass.

This paper investigates sentiment analysis in Arabic tweets that have the presence of Jordanian dialect. A new dataset was collected during the coronavirus disease (COVID-19) pandemic. We demonstrate two models: the Traditional Arabic Language (TAL) model and the Semantic Partitioning Arabic Language (SPAL) model to envisage the polarity of the collected tweets by invoking several, well-known classifiers. The extraction and allocation of numerous Arabic features, such as lexical features, writing style features, grammatical features, and emotional features, have been used to analyze and classify the collected tweets semantically. The partitioning concept was performed on the original dataset by utilizing the hidden semantic meaning between tweets in the SPAL model before invoking various classifiers. The experimentation reveals that the overall performance of the SPAL model competes over and better than the performance of the TAL model due to imposing the genuine idea of semantic partitioning on the collected dataset.

Specifying legal requirements for software systems to ensure their compliance with the applicable regulations is a major concern of requirements engineering. Personal data which is collected by an organization is often shared with other organizations to perform certain processing activities. In such cases, the General Data Protection Regulation (GDPR) requires issuing a data processing agreement (DPA) which regulates the processing and further ensures that personal data remains protected. Violating GDPR can lead to huge fines reaching to billions of Euros. Software systems involving personal data processing must adhere to the legal obligations stipulated both at a general level in GDPR as well as the obligations outlined in DPAs highlighting specific business. In other words, a DPA is yet another source from which requirements engineers can elicit legal requirements. However, the DPA must be complete according to GDPR to ensure that the elicited requirements cover the complete set of obligations. Therefore, checking the completeness of DPAs is a prerequisite step towards developing a compliant system. Analyzing DPAs with respect to GDPR entirely manually is time consuming and requires adequate legal expertise. In this paper, we propose an automation strategy that addresses the completeness checking of DPAs against GDPR provisions as a text classification problem. Specifically, we pursue ten alternative solutions which are enabled by different technologies, namely traditional machine learning, deep learning, language modeling, and few-shot learning. The goal of our work is to empirically examine how these different technologies fare in the legal domain. We computed F2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_2$$\\end{document} score on a set of 30 real DPAs. Our evaluation shows that best-performing solutions yield F2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_2$$\\end{document} score of 86.7% and 89.7% are based on pre-trained BERT and RoBERTa language models. Our analysis further shows that other alternative solutions based on deep learning (e.g., BiLSTM) and few-shot learning (e.g., SetFit) can achieve comparable accuracy, yet are more efficient to develop.

Our goal is to extract information from telephone call in order to route the call to one of number of destinations. We assume that we do not know a priori the vocabulary used in the application and so we use phonetic recognition followed by identification of salient phone sequences. In previous work, we showed that using separate language model during recognition for each route gave improved performance over using single model. However, this technique decodes each utterance in terms of the salient sequences of each call route, which leads to insertion and substitution errors that degrade performance. In this paper, we introduce the use of mixture language models for speech recognition in the context of call route classification. The benefit of technique can has the efficiency of multiple language models to get accurate recognition on salient phoneme sequences; on the other hand, it can give help in classification, even if the size of some call routes have just 50~60 utterances. It avoids building HMMs for some salient phoneme sequences to decide whether it is correct of occurring in the utterance.

In our paper we propose new technique for language modelling of highly inflectional languages such as Czech, Russian an other Slavic languages. Our aim is to alleviate main problem encountered in these languages, which is enormous vocabulary growth caused by great number of different word forms derived from one word (lemma). We reduced the size of the vocabulary by decomposing words into stems and endings and storing these sub-word units (morphemes) in the vocabulary separately. Then we trained morpheme based language model on the decomposed corpus. This paper reports perplexities, OOV rates and some speech recognition results obtained with new language model.

Automatic speech recognition systems transform speech audio data into text data, i.e., word sequences, as the recognition results. These word sequences are generally defined by the language model of the speech recognition system. Therefore, the capability of the speech recognition system to translate audio data obtained by typically pronouncing word sequences that are accepted by the language model into word sequences that are equivalent to the original ones can be regarded as a basic capability of the speech recognition systems. This work describes a testing method that checks whether speech recognition systems have this basic recognition capability. The method can verify the basic capability by performing the testing separately from recognition robustness testing. It can also be fully automated. We constructed a test automation system and evaluated though several experiments whether it could detect defects in speech recognition systems. The results demonstrate that the test automation system can effectively detect basic defects at an early phase of speech recognition development or refinement.