Biblio

In this fast-running world, machine communication plays a vital role. To compete with this world, human-machine interaction is a necessary thing. To enhance this, Natural Language Processing technique is used widely. Using this technique, we can reduce the interaction gap between the machine and human. Till now, many such applications are developed which are using this technique.This tool deals with the various methods which are used for development of grammar error correction. These methods include rule-based method, classifier-based method and machine translation-based method. Also, models regarding the Natural Language Processing (NLP) pipeline are trained and implemented in this project accordingly. Additionally, the tool can also perform speech to text operation.

The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fooling ASR systems have focused on white-box attacks, in which the model architecture and parameters are known. In this paper, we adopt a black-box approach to adversarial generation, combining the approaches of both genetic algorithms and gradient estimation to solve the task. We achieve a 89.25% targeted attack similarity, with 35% targeted attack success rate, after 3000 generations while maintaining 94.6% audio file similarity.

This paper present an approach to automate the conversion of Natural Language Query to SQL Query effectively. Structured Query Language is a powerful tool for managing data held in a relational database management system. To retrieve or manage data user have to enter the correct SQL Query. But the users who don't have any knowledge about SQL are unable to retrieve the required data. To overcome this we proposed a model in Natural Language Processing for converting the Natural Language Query to SQL query. This helps novice user to get required content without knowing any complex details about SQL. This system can also deal with complex queries. This system is designed for Training and Placement cell officers who work on student database but don't have any knowledge about SQL. In this system, user can also enter the query using speech. System will convert speech into the text format. This query will get transformed to SQL query. System will execute the query and gives output to the user.

With the developments in deep learning, the security of neural networks against vulnerabilities has become one of the most urgent research topics in deep learning. There are many types of security countermeasures. Adversarial examples and their defense methods, in particular, have been well-studied in recent years. An adversarial example is designed to make neural networks misclassify or produce inaccurate output. Audio adversarial examples are a type of adversarial example where the main target of attack is a speech-to-text transcription neural network. In this study, we propose a new defense method against audio adversarial examples for the speech-to-text transcription neural networks. It is difficult to determine whether an input waveform data representing the sound of voice is an audio adversarial example. Therefore, the main framework of the proposed defense method is based on a sandbox approach. To evaluate the proposed defense method, we used actual audio adversarial examples that were created on Deep Speech, which is a speech-to-text transcription neural network. We confirmed that our defense method can identify audio adversarial examples to protect speech-to-text systems.

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.