Recognize Foreign Low-Frequency Words with Similar Pairs

TL;DR

This paper improves automatic speech recognition of low-frequency and out-of-language words by extending a word-pair method that leverages information from multiple predicting words, enhancing probability estimates.

Contribution

It introduces an extension of the word-pair approach using multiple predicting words and applies it to multilingual speech recognition for better low-frequency word recognition.

Findings

Enhanced recognition accuracy for low-frequency words.

Effective handling of out-of-language words in multilingual ASR.

Improved probability estimation for rare words.

Abstract

Low-frequency words place a major challenge for automatic speech recognition (ASR). The probabilities of these words, which are often important name entities, are generally under-estimated by the language model (LM) due to their limited occurrences in the training data. Recently, we proposed a word-pair approach to deal with the problem, which borrows information of frequent words to enhance the probabilities of low-frequency words. This paper presents an extension to the word-pair method by involving multiple `predicting words' to produce better estimation for low-frequency words. We also employ this approach to deal with out-of-language words in the task of multi-lingual speech recognition.