Correct Recognition Errors Research Articles

FliH and FliI help FlhA bring strict order to flagellar protein export in Salmonella

The flagellar type III secretion system (fT3SS) switches substrate specificity from rod-hook-type to filament-type upon hook completion, terminating hook assembly and initiating filament assembly. The C-terminal cytoplasmic domain of FlhA (FlhAC) forms a homo-nonameric ring and is directly involved in substrate recognition, allowing the fT3SS to coordinate flagellar protein export with assembly. The highly conserved GYXLI motif (residues 368–372) of FlhAC induces dynamic domain motions of FlhAC required for efficient and robust flagellar protein export by the fT3SS, but it remains unknown whether this motif is also important for ordered protein export by the fT3SS. Here we analyzed two GYXLI mutants, flhA(GAAAA) and flhA(GGGGG), and provide evidence suggesting that the GYXLI motif in FlhAC requires the flagellar ATPase complex not only to efficiently remodel the FlhAC ring structure for the substrate specificity switching but also to correct substrate recognition errors that occur during flagellar assembly.

Research on Algorithm of Video Analysis System Based on Text Error Correction

When making a video, if the video has a language organization error, it needs to be re-recorded. It is not possible to remove inappropriate or unnatural pronunciation parts of the recording more effectively. In response to this problem, this paper studies the speech extraction, error correction and synthesis of video, which is divided into three parts: (1) Speech segmentation and speech-to-text of video; (2) Text recognition error correction; (3) Text-to-speech and video speech synthesis. For the first part, we applied the staged and efficient algorithm based on (Bayesian Information Criterion) BIC & (Statistical Mean Euclidean Distance) MEdist to segment the video voice, and then, the segmented audio is subtracted to reduce noise, and finally converted to text using the iFLYTEK interface. For the second part, we apply the (Double Automatic Error Correction) DAEC algorithm to text error correction. For the third part, we use the (Improved Chinese Realtime Voice Cloning) I-Zhrtvc for text-to-speech. Then merge the voice into the video. The simulation result shows that the staged and efficient algorithm based on BIC & MEdist, which accurately segmented by sentences, can identify audio with dialect accents, and has high accuracy in translating to text, up to an average of 95.8%. DAEC algorithm has a high error correction rate. The audio prosody accuracy after synthesis is high. ZVTOW text-to-speech (Mean Opinion Score) MOS up to 4.5.

MONITORING OF THE EDUCATIONAL PROCESS USING ARTIFICIAL INTELLIGENCE METHODS

Considered the problem of increasing the effectiveness of the educational process due to the introduction of automatic control of attendance in the classroom using face recognition and additional information for the collection and further analysis of the received data. Algorithms and methods used in modern Facial Recognition Attendance System are studied. An intelligent system for monitoring the educational process and its analysis is proposed. Structural and functional schemes of the system, databases, software were developed, testing was carried out. During attendance monitoring, the webcam captures an image of the face of the participant of the educational process from the video stream, then the computer automatically creates a vector of facial features, which is compared with the vectors of facial features, pre-entered images and recorded in the relevant database. Vectors with 68 features are used for face recognition. In the development of the software, the tools of the OpenCV library and the Python programming language were used. With several successful comparisons, the person's data is identified: name and status (student or teacher), the current date and time are recorded in an Excel file. Operational data of the system is displayed on the monitor screen, which allows you to correct recognition errors if necessary. The system allows you to automatically keep a log of class attendance, create reports, analyze data to provide recommendations for improving the schedule and order of lessons. The object-relational database with open source code PostgreSQL is used for data storage. The grouping of the system's software code is carried out using the Django web application. The system user has the opportunity to create a personal account and create reports according to his requirements. The system was tested on the example of a group of 15 students and showed satisfactory results.

The Information Content of Earnings Following Restatements

This paper examines the information content of earnings following restatements of prior period earnings. Results indicate that the information content of earnings announcements declines in periods following a restatement, but that the loss of information content is temporary. In particular, the earnings response coefficients for earnings announcements surrounding a restatement exhibit a U-shaped pattern in which they return to pre-restatement levels over an average of four quarters, suggesting that the market's concern regarding subsequently reported earnings is somewhat transitory. The extent to which the earnings of restatement firms suffer a loss of information content varies across several dimensions. First, the loss of information content is greater for firms that restate earnings to correct revenue recognition errors than it is for other types of restatements. Second, the information content of earnings is significantly lower for firms that do not make changes to their financial reporting governance structure following a restatement relative to firms that initiate governance changes. Overall, the evidence presented in this paper is consistent with a short-term decline in investor confidence regarding financial reporting following restatements, but that recovery typically takes place within four quarters.

Voice Control in Calorie Tracker Application using Levenshtein Distance Algorithm

Each food consumed by people contains a number of calories needed by the body to perform an activity. Calories can be described as fuel of engine to move and carry out tasks. Public’s indifference to the food consumed can cause some negative effects on health like, too skinny, obesity, and emergence of various diseases. Therefore, it is necessary to have an application which can provide some information about the calorie needs, so that user can control the calorie intake. This paper describes the development of an application to assist user in controlling calorie intake according to the calorie needs. This application supports voice control feature to improve user comfort in performing certain commands and inputting food consumed. In addition, this application also uses Levenshtein Distance algorithm to correct food recognition errors which is spoken by user. This application is developed using Java programming language for Android with SQLite database.

Intelligent information technology building systems diagnostics using nuclear moments Volterra

The paper presents the intelligent information technology to increase the efficiency of diagnosing the state of nonlinear dynamical objects of different physical nature with the use of mathematical models in the form of Volterra kernels. Research results on the test object monitoring show that moments of nuclei Volterra 2nd order characterized by the highest stability of the quality of diagnosis (probability of correct recognition) errors in measuring the response of objects of control compared to the data of their classification on the basis of samples of nuclei with a given increment. Figs.: 5. Tabl.: 2. Refs.: 13 titles.Keywords: intelligent information technology; systems diagnostics; Volterra kernels; mathematical models in the form of Volterra kernels; quality of diagnosis.

Weighted finite-state transducer-based dysarthric speech recognition error correction using context-dependent pronunciation variation modelling

In this paper, an error correction method is proposed to improve the performance of dysarthric automatic speech recognition (ASR). To this end, context-dependent pronunciation variations are modelled by using a weighted Kullback-Leibler (KL) distance between acoustic models of ASR. Then, the context-dependent pronunciation variation model is converted into a weighted finite-state transducer (WFST) and combined with a lexicon and a language model. It is shown from ASR experiments that average word error rate (WER) of a WFST-based ASR system with the proposed error correction method is relatively reduced by 19.73%, compared to an ASR system without error correction. Moreover, it is shown that the error correction method using a weighted KL distance relatively reduces average WER by 3.81%, compared to that using a KL distance.

A Multilayer Hidden Markov Models-Based Method for Human-Robot Interaction

To achieve Human-Robot Interaction (HRI) by using gestures, a continuous gesture recognition approach based on Multilayer Hidden Markov Models (MHMMs) is proposed, which consists of two parts. One part is gesture spotting and segment module, the other part is continuous gesture recognition module. Firstly, a Kinect sensor is used to capture 3D acceleration and 3D angular velocity data of hand gestures. And then, a Feed-forward Neural Networks (FNNs) and a threshold criterion are used for gesture spotting and segment, respectively. Afterwards, the segmented gesture signals are respectively preprocessed and vector symbolized by a sliding window and a K-means clustering method. Finally, symbolized data are sent into Lower Hidden Markov Models (LHMMs) to identify individual gestures, and then, a Bayesian filter with sequential constraints among gestures in Upper Hidden Markov Models (UHMMs) is used to correct recognition errors created in LHMMs. Five predefined gestures are used to interact with a Kinect mobile robot in experiments. The experimental results show that the proposed method not only has good effectiveness and accuracy, but also has favorable real-time performance.

Speech Recognition Error Compensation using MFCC and LPC Feature Extraction Method

Speech recognition system is input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Therefore, in this paper, we propose a speech recognition error correction method using phoneme similarity rate and reliability measures based on the characteristics of the phonemes. Phonemes similarity rate was phoneme of learning model obtained used MFCC and LPC feature extraction method, measured with reliability rate. Minimize the error to be unrecognized by measuring the rate of similar phonemes and reliability. Turned out to error speech in the process of speech recognition was error compensation performed. In this paper, the result of applying the proposed system showed a recognition rate of 98.3%, error compensation rate 95.5% in the speech recognition.

Whole-Book Recognition

Whole-book recognition is a document image analysis strategy that operates on the complete set of a book's page images using automatic adaptation to improve accuracy. We describe an algorithm which expects to be initialized with approximate iconic and linguistic models--derived from (generally errorful) OCR results and (generally imperfect) dictionaries--and then, guided entirely by evidence internal to the test set, corrects the models which, in turn, yields higher recognition accuracy. The iconic model describes image formation and determines the behavior of a character-image classifier, and the linguistic model describes word-occurrence probabilities. Our algorithm detects "disagreements" between these two models by measuring cross entropy between 1) the posterior probability distribution of character classes (the recognition results resulting from image classification alone) and 2) the posterior probability distribution of word classes (the recognition results from image classification combined with linguistic constraints). We show how disagreements can identify candidates for model corrections at both the character and word levels. Some model corrections will reduce the error rate over the whole book, and these can be identified by comparing model disagreements, summed across the whole book, before and after the correction is applied. Experiments on passages up to 180 pages long show that when a candidate model adaptation reduces whole-book disagreement, it is also likely to correct recognition errors. Also, the longer the passage operated on by the algorithm, the more reliable this adaptation policy becomes, and the lower the error rate achieved. The best results occur when both the iconic and linguistic models mutually correct one another. We have observed recognition error rates driven down by nearly an order of magnitude fully automatically without supervision (or indeed without any user intervention or interaction). Improvement is nearly monotonic, and asymptotic accuracy is stable, even over long runs. If implemented naively, the algorithm runs in time quadratic in the length of the book, but random subsampling and caching techniques speed it up by two orders of magnitude with negligible loss of accuracy. Whole-book recognition has potential applications in digital libraries as a safe unsupervised anytime algorithm.

Supporting dictation speech recognition error correction: the impact of external information

Although speech recognition technology has made remarkable progress, its wide adoption is still restricted by notable effort made and frustration experienced by users while correcting speech recognition errors. One of the promising ways to improve error correction is by providing user support. Although support mechanisms have been proposed for inline speech recognition error correction, how to develop user support for third-party error correction has been under studied. To address the unique challenges associated with third-party error correction, external information that is obtained outside of an erroneous sentence was employed in this research. Specifically, three types of external information were selected, including word alternative hypotheses, noisy context and accurate context, and their impacts on dictation speech recognition error correction were assessed empirically. As expected, results revealed the importance of context information to improving both the performance and perception of error correction. Additionally, the results also provided insights into possible effects of word error rate and sentence length on error correction. These findings have significant implications to interface design for transcript proofreading systems.

Intelligently Aiding Human-Guided Correction of Speech Recognition

Correcting recognition errors is often necessary in a speech interface. These errors not only reduce users' overall entry rate, but can also lead to frustration. While making fewer recognition errors is undoubtedly helpful, facilities for supporting user-guided correction are also critical. We explore how to better support user corrections using Parakeet — a continuous speech recognition system for mobile touch-screen devices. Parakeet's interface is designed for easy error correction on a handheld device. Users correct errors by selecting alternative words from a word confusion network and by typing on a predictive software keyboard. Our interface design was guided by computational experiments and used a variety of information sources to aid the correction process. In user studies, participants were able to write text effectively despite sometimes high initial recognition error rates. Using Parakeet as an example, we discuss principles we found were important for building an effective speech correction interface.

PodCastle: A Spoken Document Retrieval System Improved by User Contributions

In this paper, we describe a public web service, ``PodCastle'', that provides full-text searching of speech data (Japanese podcasts) on the basis of automatic speech recognition technologies. This is an instance of our research approach, ``Speech Recognition Research 2.0'', which is aimed at providing users with a web service based on Web 2.0 so that they can experience state-of-the-art speech recognition performance, and at promoting speech recognition technologies in cooperation with anonymous users. PodCastle enables users to find podcasts that include a search term, read full texts of their recognition results, and easily correct recognition errors by simply selecting from a list of candidates. Even if a state-of-the-art speech recognizer is used to recognize podcasts on the web, a number of errors will naturally occur. PodCastle therefore encourages users to cooperate by correcting these errors so that those podcasts can be searched more reliably. Furthermore, using the resulting corrections to train the speech recognizer, it implements a mechanism whereby the speech recognition performance is gradually improved. Our experience with this web service showed that user contributions we collected actually improved the performance of PodCastle.

BioTagger-GM: A Gene/Protein Name Recognition System

Biomedical named entity recognition (BNER) is a critical component in automated systems that mine biomedical knowledge in free text. Among different types of entities in the domain, gene/protein would be the most studied one for BNER. Our goal is to develop a gene/protein name recognition system BioTagger-GM that exploits rich information in terminology sources using powerful machine learning frameworks and system combination. BioTagger-GM consists of four main components: (1) dictionary lookup-gene/protein names in BioThesaurus and biomedical terms in UMLS Metathesaurus are tagged in text, (2) machine learning-machine learning systems are trained using dictionary lookup results as one type of feature, (3) post-processing-heuristic rules are used to correct recognition errors, and (4) system combination-a voting scheme is used to combine recognition results from multiple systems. The BioCreAtIvE II Gene Mention (GM) corpus was used to evaluate the proposed method. To test its general applicability, the method was also evaluated on the JNLPBA corpus modified for gene/protein name recognition. The performance of the systems was evaluated through cross-validation tests and measured using precision, recall, and F-Measure. BioTagger-GM achieved an F-Measure of 0.8887 on the BioCreAtIvE II GM corpus, which is higher than that of the first-place system in the BioCreAtIvE II challenge. The applicability of the method was also confirmed on the modified JNLPBA corpus. The results suggest that terminology sources, powerful machine learning frameworks, and system combination can be integrated to build an effective BNER system.

ASR post-correction for spoken dialogue systems based on semantic, syntactic, lexical and contextual information

This paper proposes a technique to correct speech recognition errors in spoken dialogue systems that presents two main novel contributions. On the one hand, it considers several contexts where a speech recognition result can be corrected. A threshold learnt in the training is used to decide whether the correction must be carried out in the context associated with the current prompt type of a dialogue system, or in another context. On the other hand, the technique deals with the confidence scores of the words employed in the corrections. The correction is carried out at two levels: statistical and linguistic. At the first level the technique employs syntactic–semantic and lexical models, both contextual, to decide whether a recognition result is correct. According to this decision the recognition result may be changed. At the second level the technique employs basic linguistic knowledge to decide about the grammatical correctness of the outcome of the first level. According to this decision the outcome may be changed as well. Experimental results indicate that the technique enhances a dialogue system’s word accuracy, speech understanding, implicit recovery and task completion rates by 8.5%, 16.54%, 4% and 44.17%, respectively.

An Empirical Analysis of the Decline in the Information Content of Earnings Following Restatements

Regulatory officials and market analysts have speculated that the loss of credibility in subsequently reported financial information is a long-lasting consequence of earnings restatements. I measure the information content of earnings using a standard earnings-returns framework over several years surrounding restatements to examine characteristics of the decline in the information content of earnings. Results indicate that although the information content of earnings declines following restatements, the loss is temporary. In particular, the earnings response coefficients for earnings announcements surrounding restatements exhibit a U-shaped pattern in which they are no longer significantly lower in the post-restatement period over an average of four quarters. The extent to which the earnings of restatement firms suffer a loss of information content varies across several dimensions. First, the duration of the loss is greater for firms that restate earnings to correct revenue recognition errors and for restatements that result in a large decline in the stock price at the announcement date. Second, there is not a loss in the information content of earnings for firms that make changes to their financial reporting governance structures following restatements. Overall, the evidence in this paper is consistent with a short-term decline in investor confidence regarding financial reporting following restatements, but shows that suspicion regarding the information loss of post-restatement earnings in the long-term is unwarranted.

Using Airport Layout Information to Improve Automatic Speech Recognition for Digitizing Taxi Instructions

During taxiing, an Electronic Flight Bag (EFB) showing airport and route-data can support pilots. In the present study, the possibility of using a Voice Recognition System (VRS) to enable pilots to enter route instructions, for usage in situations where digital data link is not available, was investigated. The potential of techniques that utilize information on airport layout to detect and correct voice recognition errors was explored. Experiment I investigated the accuracy rates that can be achieved with the basic VRS. Although high, the resulting accuracy was insufficient, for safety reasons as well as user-acceptance of the system. A configurable system that interprets user utterances based on possible taxi routes on the airport, was designed and implemented. Experiment II explored the potential improvement of the different configuration options on error detection and correction performance. With one of the configurations, an increase of 42% in overall recognition rates was achieved.

Data mining for detecting errors in dictation speech recognition

The efficiency promised by a dictation speech recognition (DSR) system is lessened by the need for correcting recognition errors. Error detection is the precursor of error correction. Developing effective techniques for error detection can thus lead to improved error correction. Current research on error detection has focused mainly on transcription and/or domain-specific speech. Error detection in DSR has been studied less. We propose data mining models for detecting errors in DSR. Instead of relying on internal parameters from DSR systems, we propose a loosely coupled approach to error detection based on features extracted from the DSR output. The features mainly came from two sources: confidence scores and linguistics parsing. Link grammar was innovatively applied to error detection. Three data mining techniques, including Na/spl inodot//spl uml/ve Bayes, neural networks, and Support Vector Machines (SVMs), were evaluated on 5M DSR corpora. The experimental results showed that significant performance was achieved in that F-measures for error detection ranged from 55.3% to 62.5%. This study provided insights into the merit of different data-mining techniques and different types of features in error detection.

Multimodal error correction for speech user interfaces

Although commercial dictation systems and speech-enabled telephone voice user interfaces have become readily available, speech recognition errors remain a serious problem in the design and implementation of speech user interfaces. Previous work hypothesized that switching modality could speed up interactive correction of recognition errors. This article presents multimodal error correction methods that allow the user to correct recognition errors efficiently without keyboard input. Correction accuracy is maximized by novel recognition algorithms that use context information for recognizing correction input. Multimodal error correction is evaluated in the context of a prototype multimodal dictation system. The study shows that unimodal repair is less accurate than multimodal error correction. On a dictation task, multimodal correction is faster than unimodal correction by respeaking. The study also provides empirical evidence that system-initiated error correction (based on confidence measures) may not expedite error correction. Furthermore, the study suggests that recognition accuracy determines user choice between modalities: while users initially prefer speech, they learn to avoid ineffective correction modalities with experience. To extrapolate results from this user study, the article introduces a performance model of (recognition-based) multimodal interaction that predicts input speed including time needed for error correction. Applied to interactive error correction, the model predicts the impact of improvements in recognition technology on correction speeds, and the influence of recognition accuracy and correction method on the productivity of dictation systems. This model is a first step toward formalizing multimodal interaction.

Automated Reading of Cheque Amounts

This paper describes a complete system for the automated reading of amounts extracted from bank and postal cheques. We focus our description on the steps where we developed and applied new techniques. These are the reading of the legal amount and the cross-validation of the recognition results for the legal and courtesy amount. In our work we deal with German cheque amounts. The reading of German legal amounts is a special challenge, since the literal words the legal amount is constructed of are usually completely connected. For the cross-validation step, we present a well structured combination strategy that allows detecting and correcting recognition errors for the legal and courtesy amount and leads to a significant increase in the system performance. Our system was tested on a database with real cheques from Swiss postal services.