Recognize Foreign Low-Frequency Words with Similar Pairs

06/16/2015
by   Xi Ma, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/05/2021

Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition

Neural sequence-to-sequence systems deliver state-of-the-art performance...
research
05/31/2021

More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods

This paper presents a comparison of unsupervised methods of hypernymy pr...
research
07/16/2021

A Comparison of Methods for OOV-word Recognition on a New Public Dataset

A common problem for automatic speech recognition systems is how to reco...
research
09/27/1998

Similarity-Based Models of Word Cooccurrence Probabilities

In many applications of natural language processing (NLP) it is necessar...
research
08/10/2019

Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription

In Indian Languages , native speakers are able to understand new words f...
research
03/29/2022

Short-Term Word-Learning in a Dynamically Changing Environment

Neural sequence-to-sequence automatic speech recognition (ASR) systems a...
research
03/19/2020

Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems

The problem of out of vocabulary words (OOV) is typical for any speech r...

Please sign up or login with your details

Forgot password? Click here to reset