CLJun 16, 2015

Recognize Foreign Low-Frequency Words with Similar Pairs

arXiv:1506.04940v15 citations
Originality Synthesis-oriented
AI Analysis

This work addresses a specific problem in ASR for handling rare words, but it is incremental as it builds on an existing word-pair approach.

The paper tackles the challenge of low-frequency and out-of-language words in automatic speech recognition by extending a word-pair method to use multiple predicting words for better probability estimation, achieving unspecified improvements in multi-lingual tasks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes