Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR

06/27/2018
by   Yerbolat Khassanov, et al.
0

In automatic speech recognition (ASR) systems, recurrent neural network language models (RNNLM) are used to rescore a word lattice or N-best hypotheses list. Due to the expensive training, the RNNLM's vocabulary set accommodates only small shortlist of most frequent words. This leads to suboptimal performance if an input speech contains many out-of-shortlist (OOS) words. An effective solution is to increase the shortlist size and retrain the entire network which is highly inefficient. Therefore, we propose an efficient method to expand the shortlist set of a pretrained RNNLM without incurring expensive retraining and using additional training data. Our method exploits the structure of RNNLM which can be decoupled into three parts: input projection layer, middle layers, and output projection layer. Specifically, our method expands the word embedding matrices in projection layers and keeps the middle layers unchanged. In this approach, the functionality of the pretrained RNNLM will be correctly maintained as long as OOS words are properly modeled in two embedding spaces. We propose to model the OOS words by borrowing linguistic knowledge from appropriate in-shortlist words. Additionally, we propose to generate the list of OOS words to expand vocabulary in unsupervised manner by automatically extracting them from ASR output.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/17/2023

Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam

In a hybrid automatic speech recognition (ASR) system, a pronunciation l...
research
05/26/2022

Contextual Adapters for Personalized Speech Recognition in Neural Transducers

Personal rare word recognition in end-to-end Automatic Speech Recognitio...
research
09/22/2019

Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR

Acoustic-to-word (A2W) end-to-end automatic speech recognition (ASR) sys...
research
05/22/2017

Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition

With the evolution of neural network based methods, automatic speech rec...
research
11/07/2020

Naturalization of Text by the Insertion of Pauses and Filler Words

In this article, we introduce a set of methods to naturalize text based ...
research
09/15/2020

Improving Joint Layer RNN based Keyphrase Extraction by Using Syntactical Features

Keyphrase extraction as a task to identify important words or phrases fr...

Please sign up or login with your details

Forgot password? Click here to reset