Phone-duration-based confidence measures for embedded applications

Proper nouns are usually primary keys in a query. Their correct translation might be necessary to maintain a good retrieval performance in a cross language information retrieval (CLIR) system. However, dictionaries only include the most commonly used proper nouns, like major countries and capitals. As they are spelling variants of each other in most languages, using an approximate string matching technique against the target database index is the common approach taken to find the target language correspondents of the original query key. N-gram technique proved to be the most effective among other approximate string matching techniques. As we are dealing with an English-Arabic CLIR system which involves two languages of different alphabets, we decided to combine transliteration with the n-gram technique to generate the different spelling variants of out of vocabulary (OOV) words. We call this technique: Transliteration Ngram (TNG). One issue that arises with the Arabic language is that words that are spelled similarly can have different meanings depending on the context of the sentence. This is particularly true for proper names, which usually have a meaning if used as a verb or adjective. To further enhance our transliteration approach, we chose to use part of speech (POS) disambiguation to reduce the number of unrelated words from the set transliterations obtained using TNG.

We present a method for open vocabulary retrieval based on a spoken document retrieval (SDR) system using subword models. The present paper proposes a new approach to open vocabulary SDR system using subword models which do not require subword recognition. Instead, subword sequences are obtained from the phone sequence outputted containing an out of vocabulary (OOV) word, a speech recognizer outputs a word sequence whose phone sequence is considered to be similar to the OOV word. When OOV words are provided in a query, the proposed system is able to retrieve the target section by comparing the phone sequences of the query and the word sequence generated by the speech recognizer.

This paper sheds light on a system that would be able to diacritize Arabic texts automatically (SHAKKIL). In this system, the diacritization problem will be handled through two levels; morphological and syntactic processing levels. The adopted morphological disambiguation algorithm depends on four layers; Uni-morphological form layer, rule-based morphological disambiguation layer, statistical-based disambiguation layer and Out Of Vocabulary (OOV) layer. The adopted syntactic disambiguation algorithms is concerned with detecting the case ending diacritics depending on a rule based approach simulating the shallow parsing technique. This will be achieved using an annotated corpus for extracting the Arabic linguistic rules, building the language models and testing the system output. This system is considered as a good trial of the interaction between rule-based approach and statistical approach, where the rules can help the statistics in detecting the right diacritization and vice versa. At this point, the morphological Word Error Rate (WER) is 4.56% while the morphological Diacritic Error Rate (DER) is 1.88% and the syntactic WER is 9.36%. The best WER is 14.78% compared to the best-published results, of (Abandah, 2015); 11.68%, (Rashwan, et al., 2015); 12.90% and (Metwally, Rashwan, & Atiya, 2016); 13.70%.

This chapter presents the results achieved by modeling cross-word pronunciation variation problem of MSA. We practically investigated two MSA phonological rules (Idgham and Iqlaab) which significantly enhanced recognition accuracy. Three ASR’s metrics were measured: word error rate (WER), out of vocabulary (OOV), and perplexity (PP).

Passive sensing applications are limited by their inability to determine who is using a device, a critical concern in child mobile device use research, where devices are often shared between siblings or between a child and their parent. Our previous work leveraged behavioral biometrics to identify a target child user; however, it is unknown what type of training data is necessary for optimal model performance. This study evaluated model performance across different characteristics of training data. Thirty-six children (11.3 ± 0.9 years, 56% female) self-selected a video or a game on iPads for 10 min while laying and for another 5 min while sitting. The SensorLog application captured iPad accelerometer and gyroscope data while the child interacted with the device. Machine learning algorithms including Neural Network (NN), Random Forest (RF), k-Nearest Neighbors (k-NN), and SwipeFormer were applied to determine the most important aspects of training data to optimize model performance. The aspects of training data evaluated included (1) varying the length (i.e., seconds of training data), (2) varying the user position (i.e., sitting, laying), and (3) varying the time proximity between training and testing data. F1 score was used to evaluate model performance. The SwipeFormer F1 scores were lowest when the training data was further from the test data (0 when training data was 11 min away from test data) and highest when training data was close to test data (0.91 when training data was the minute preceding test data). The SwipeFormer F1 scores were highest when predicting the user laying from laying (0.97) and sitting from sitting (0.94), and lowest when predicting the user sitting from laying (0) and laying from sitting (0). The length of training data had little impact on performance, with a SwipeFormer F1 score of 0.91 when training on one minute of data and a SwipeFormer F1 score of 0.94 when training on twelve minutes of data. Because researchers would likely be predicting users at different timepoints than their training data, research should focus on improving model performance for identifying users independent of time proximity for training and test data.

Towards a Novel Weakly Supervised Joint Approach of Named Entity Recognition and Normalization for Noisy Text

Morpho-syntactic post-processing of N-best lists for improved French automatic speech recognition

Semantic representations of words have been successfully extracted from unlabeled corpuses using neural network models like word2vec. These representations are generally high quality and are computationally inexpensive to train, making them popular. However, these approaches generally fail to approximate out of vocabulary (OOV) words, a task humans can do quite easily, using word roots and context clues. This paper proposes a neural network model that learns high quality word representations, subword representations, and context clue representations jointly. Learning all three types of representations together enhances the learning of each, leading to enriched word vectors, along with strong estimates for OOV words, via the combination of the corresponding context clue and subword embeddings. Our model, called Estimator Vectors (EV), learns strong word embeddings and is competitive with state of the art methods for OOV estimation.

In Indian Languages, root words will be either combined or modified to match the context with reference to tense, number and/or gender. So the number of unique words will increase when compared to many European languages. Whatever be the size of the text corpus used for language modeling cannot contain all the possible inflected words. A word which occurred during testing but not in training data is called Out of Vocabulary (OOV) word. Similarly, the text corpus cannot have all possible sequence of words. So Due to this data sparsity, Automatic Speech Recognition system (ASR) may not accommodate all the words in the language model/irrespective of the size of the text corpus. It also becomes computationally challenging if the volume of the data increases exponentially due to morphological changes to the root word. To reduce the OOVs in the language model, a new unsupervised stemming method is proposed in this paper for one Indian language, Telugu, based on the method proposed for Hindi. Other issues in the language modeling for Telugu using techniques like smoothing and interpolation, with supervised and unsupervised stemming data is also analyzed. It is observed that the smoothing techniques Witten–Bell and Kneser–Ney performing well when compared to other techniques, on pre-processed data with supervised learning. The ASRs accuracy is improved by 0.76% and 0.94% with supervised and unsupervised stemming respectively.

Summary is the task of compressing a piece of text into a short version with the main information of the original text. While previous architecture choices revolve around Convolutional Neural Networks (CNN) and long shortterm memory (LSTM) recurrent neural networks, recently self-attention and transformer have been used for the text generation task and achieved very good results. However transformer lacks local attention information and uses simple calculations as address vectors. In our article, we put forward a new seq-to-seq model for generating text summary called LTABS (Abstractive summarization on LSTM and Transformer). This model makes transformer be more suitable for summary generation tasks. For the encoder part of the model, we make use of the hidden layer result of LSTM as the location information. At the same time, transformer is used as the attention matrix of LSTM. This design allows the transformer to obtain location information and enhance local attention. We add copy mechanism to the new network to finish off the summary tasks OOV (out of vocabulary) problem. We apply our model to CNN and Daily Mail and Xsum datasets, the test outcome shows that the LTABS framework is superior to the most advanced model in semantic and syntactic structure, and has achieved competitive results in manual language quality assessment.

Efficient acoustic feature transformation in mismatched environments using a Guided-GAN

A method and an apparatus for improved duration modeling of phonemes in a speech synthesis system are provided. According to one aspect, text is received into a processor of a speech synthesis system. The received text is processed using a sum-of-products phoneme duration model that is used in either the formant method or the concatenative method of speech generation. The phoneme duration model, which is used along with a phoneme pitch model, is produced by developing a non-exponential functional transformation form for use with a generalized additive model. The non-exponential functional transformation form comprises a root sinusoidal transformation that is controlled in response to a minimum phoneme duration and a maximum phoneme duration. The minimum and maximum phoneme durations are observed in training data. The received text is processed by specifying at least one of a number of contextual factors for the generalized additive model. An inverse of the non-exponential functional transformation is applied to duration observations, or training data. Coefficients are generated for use with the generalized additive model. The generalized additive model comprising the coefficients is applied to at least one phoneme of the received text resulting in the generation of at least one phoneme having a duration. An acoustic sequence is generated comprising speech signals that are representative of the received text.

Towards a Novel Weakly Supervised Joint Approach of Named Entity Recognition and Normalization for Noisy Text

This focus issue of Physiological Measurement follows the 38th Annual International Computing in Cardiology (CinC) Conference, hosted in Hangzhou, China in September 2011 by Zhejiang University. Each year, the NIH-sponsored PhysioNet resource (http://physionet.org/) runs an open competition lasting several months, aimed at encouraging the development of solutions to an unsolved or poorly solved problem in biomedicine, in most cases making use of relevant clinical and experimental data provided freely by PhysioNet. Participants in these annual challenges discuss their diverse approaches to the Challenge problems during dedicated scientific sessions at CinC. The topics of these PhysioNet/CinC Challenges range from physiologic signal processing and analysis to forecasting and modelling clinically important events and processes.

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.