A LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SYSTEM FOR HINDI (original) (raw)

paper cover icon

A LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SYSTEM FOR HINDI

2002

Chalapathy Neti

Ashish Verma

Nitendra Rajput

Abstract

In this paper we present a Hindi Speech Recognition system which has been trained on 40 hours of audio data and a has a trigram language model that is trained with 3 million words. For a vocabulary size of 65000 words, the system gives a word accuracy of 75% to 95%.

Chalapathy Neti hasn't uploaded this paper.

Let Chalapathy know you want this paper to be uploaded.

Ask for this paper to be uploaded.