A large-vocabulary continuous speech recognition system for Hindi

TLDR: This paper presents two new techniques that have been used to build a large-vocabulary continuous Hindi speech recognition system and proposes a hybrid approach that combines rule-based and statistical approaches in a two-step fashion.

Abstract: In this paper we present two new techniques that have been used to build a large-vocabulary continuous Hindi speech recognition system. We present a technique for fast bootstrapping of initial phone models of a new language. The training data for the new language is aligned using an existing speech recognition engine for another language. This aligned data is used to obtain the initial acoustic models for the phones of the new language. Following this approach requires less training data. We also present a technique for generating baseforms (phonetic spellings) for phonetic languages such as Hindi. As is inherent in phonetic languages, rules generally capture the mapping of spelling to phonemes very well. However, deep linguistic knowledge is required to write all possible rules, and there are some ambiguities in the language that are difficult to capture with rules. On the other hand, pure statistical techniques for base and generation require large amounts of training data that are not readily available. We propose a hybrid approach that combines rule-based and statistical approaches in a two-step fashion. We evaluate the performance of the proposed approaches through various phonetic classification and recognition experiments.