Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users

نویسندگان

چکیده

For many of the 700 million illiterate people around world, speech recognition technology could provide a bridge to valuable information and services. Yet, those most in need this are often underserved by it. In countries, tend speak only low-resource languages, for which datasets necessary development scarce. paper, we investigate effectiveness unsupervised representation learning on noisy radio broadcasting archives, abundant even languages. We make three core contributions. First, release two research community. The first, West African Radio Corpus, contains 142 hours audio more than 10 languages with labeled validation subset. second, Virtual Assistant Speech Recognition consists 10K clips four Next, share wav2vec, encoder trained corpus, compare it baseline Facebook six times data higher quality. show that wav2vec performs similarly multilingual task, significantly outperforms language identification task. Finally, first-ever models Maninka, Pular Susu, spoken combined over seven including where majority adult population is illiterate. Our contributions offer path forward ethical AI serve needs disadvantaged digital divide.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Expert System as an Intelligent Assistant for Computer Users

This paper is concerned w i t h a new implement a t i o n of a product ion system by using a r e l a t i o n a l DBMS and FORTRAN and i t s a p p l i c a t i o n to c o n s t r u c t i o n o f a n i n t e l l i g e n t m a n m a c h i n e i n t e r f a c e of a speech database c a l l e d SPEECH-DB. Our P r o d u c t i o n s y s t e m can be v i e w e d as a nonde te rmin is t i c FORTRAN progr...

متن کامل

Intelligent Virtual Assistant for Gamified Environments

Gamification aims at improving people's motivation and performance in certain tasks by introducing different mechanics taken from traditional games. Gamification has been successfully applied in different domains, such as education, marketing, and the workplace. In this paper we present an intelligent virtual assistant for gamified environments. This assistant will provide the players with help...

متن کامل

Towards a Digital Money Structure for illiterate Users

In developing countries, although money is becoming digital in the form of mobile money, it is not easily used by millions of illiterate users in their everyday transactions. Digitization of material money thus poses a challenge to many users. Existing mobile money systems and platforms represent money in terms of simple numbers, like 13, 50, 0.78, 23.64, 80 etc. This way of money representatio...

متن کامل

Assistant-Based Speech Recognition for ATM Applications

—Situation awareness of today’s automation relies so far on sensor information, data bases and the information delivered by the operator using an appropriate user interface. Listening to the conversation of people is not addressed until today, but an asset in many working situations of teams. This paper shows that automatic speech recognition (ASR) integrating into air traffic management applic...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence

سال: 2021

ISSN: ['2159-5399', '2374-3468']

DOI: https://doi.org/10.1609/aaai.v35i17.17733