Meta-Learning for improving rare word recognition in end-to-end ASR

02/25/2021
by   Florian Lux, et al.
0

We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining their outcomes into an end-to-end automatic speech recognition system to improve rare word recognition. We verify the functionality of each of our three contributions in two experiments exploring their performance for different amounts of classes (N-way) and examples per class (k-shot) in a few-shot setting. We find that the speech embeddings work well and the changes to the meta learning approaches also clearly enable them to perform continuous signal spotting. Despite the interface between keyword spotting and speech recognition being very simple, we are able to consistently improve word error rate by up to 5

READ FULL TEXT
research
11/10/2018

Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling

In recent years, end-to-end models have become popular for application i...
research
07/23/2023

A meta learning scheme for fast accent domain expansion in Mandarin speech recognition

Spoken languages show significant variation across mandarin and accent. ...
research
03/04/2020

Learning Fast Adaptation on Cross-Accented Speech Recognition

Local dialects influence people to pronounce words of the same language ...
research
11/23/2020

Multi-task Language Modeling for Improving Speech Recognition of Rare Words

End-to-end automatic speech recognition (ASR) systems are increasingly p...
research
11/11/2019

Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning

End-to-end Speech Translation (ST) models have several advantages such a...
research
12/26/2018

Meta Learning for Few-shot Keyword Spotting

Keyword spotting with limited training data is a challenging task which ...
research
02/24/2022

Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition

Children's automatic speech recognition (ASR) is always difficult due to...

Please sign up or login with your details

Forgot password? Click here to reset