Team Shabdha

Our Project, Automatic Audio Replacement of Objectionable Content for Sri Lankan Locale, is mainly based on Digital Signal Processing (DSP), Natural Language Processing (NLP), and Speech Recognition. Among them, the audio pre-processing phase, which mainly focuses on the Digital Signal Processing is the area I worked on, and this article briefs the progress of that part in our project. The DSP portion of our implemented system mainly has two focuses.  1. Noise Reduction 2. Amplification Audio inputs of the users might be of varying qualities and they might be recorded under different environmental conditions. In order to proceed ahead with our system, and to detect objectionable content efficiently and accurately, having cleaned audios are important. Hence, when a user inputs an audio into the system, it will first go through the noise reduction process. We have tried various filters for our audio samples, and finally, we came into a conclusion that ...

Since the beginning of our project, as a team, we have been doing background studies on the concepts involved in our project namely, Digital Signal Processing, Speech Recognition and Natural language processing (NLP). I have been handling the NLP aspect of our project for the past months and we have arrived at some conclusions relevant to our scope.  As per Wikipedia,  NLP is a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human languages, in particular how to program computers to process and analyze large amounts of natural language data. According to the methodology mentioned above, following the audio signal analysis and speech to text conversion, the NLP module detects the offensive profanity using Machine Learning. So far, we have implemented the machine learning model for English with around 96% using an opensource training dataset which consists of t...

We could find a considerable amount of research work with regard to our project idea “ A system for Automatic Audio Replacement of Objectionable Content for Sri Lankan Locale ”.Most of the researches were based on English.  These are the brief summaries about the most related research work- 01) Automatic Replacement of Objectionable Audio Content from Audio Signals, A. Stuart, R. Sahasrabudhe and S. Kendal. (2009, February 26). Patent US 20090055189A1 [Online]. Available: https://patentimages.storage.googleapis.com/43/46/1a/0a948544e9c839/US20090055189 A1.pdf This research paper is very much similar to our proposed project but it is a hardware solution specifically for the English language. This will first filter objectionable content from a real-time audio signal, identifies the type of objectionable content and replaces them with an audio clip corresponding to the replacement setting.  02)Filtering some Portions of a Multimedia Stream,...

We are proposing a method that can easily find and replace the objectionable content in an audio file using an artificial intelligence model. This method will be useful for the media editors, since they can easily find and replace the objectionable content in the audio file with one click. He can input the audio file and select the objectionable content type. After that our system will automatically find and replace the objectionable content with the predefined words or phrases. The replaced words are intended to match with the voice and the modulation of the original input.  When the program starts to run, the user will have the ability to input an audio file(wav or mp3) to be analyzed. Thereafter the audio clip will be analyzed and filtered out the noise using several filters (eg: Low pass, High Pass, etc.). Following that, the user can choose what specific objectionable audio content should be identified and replaced. The program will provide four options namely...

We thought of conducting a survey, in order to gather some information for our research based project. For that we prepared three forms in Sinhala, Tamil and English languages, since they are the most widely used languages in Sri Lanka. We started distributing our forms through social media on 7th July, 2019 and our expectation is to get 500 responses. At the moment, we have succeeded in getting around 350 responses from all the 3 surveys. Here we have asked 8 questions, which are related to our research. Our 1st question is aimed to know the background of the person who fills the form. In order to get the details, we have given some options like undergraduate, graduate, academic  and other Professional. According to the responses we got from all three languages, the most who filled the form are "undergraduates". Our 2nd question is to know the gender. None had not mentioned that they dislike to state their gender. But we gave such an option in...

In today's world, audiovisual media plays a significant role in impacting the society at large. The media content a person is exposed to naturally affects the way he thinks and behaves. Hence, it is important to pay attention towards the content of media. In the present, majority of the audiovisual  media content which people watch or listen to, undeniably features some form of objectionable content, such as hate speech, crude language, ethnic and racial slurs, which none of us, should be exposed to. Identifying this issue, several parties all around the world have made several recorded attempts to resolve this problem through various implementations with the use of various technologies. Yet, the above mentioned issue remains as an issue unaddressed for us here in Sri Lanka, since all those parties have focused their concern mainly on English Language. Sri Lanka is a country, which is well known for its rich cultural and traditional values. O ver 15 million people, whi...