Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets

10/09/2021
by   Jimmy Tobin, et al.
0

This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with different types and severities of speech impairment with training sets ranging in size from <1 minute to 18-20 minutes of speech data. Word error rate (WER) thresholds were selected to determine Success Percentage (the percentage of personalized models reaching the target WER) in different application scenarios. For the home automation scenario, 79 WER with 18-20 minutes of speech; but even with only 3-4 minutes of speech, 63 of speakers reached the target WER. Further evaluation found similar improvement on test sets with conversational and out-of-domain, unprompted phrases. Our results demonstrate that with only a few minutes of recordings, individuals with disordered speech could benefit from personalized ASR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/31/2019

Personalizing ASR for Dysarthric and Accented Speech with Limited Data

Automatic speech recognition (ASR) systems have dramatically improved ov...
research
06/18/2021

On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech

While current state-of-the-art Automatic Speech Recognition (ASR) system...
research
10/31/2022

An analysis of degenerating speech due to progressive dysarthria on ASR performance

Although personalized automatic speech recognition (ASR) models have rec...
research
03/27/2023

Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis

Adapting generic speech recognition models to specific individuals is a ...
research
06/08/2023

Latent Phrase Matching for Dysarthric Speech

Many consumer speech recognition systems are not tuned for people with s...
research
08/06/2019

Practical Speech Recognition with HTK

The practical aspects of developing an Automatic Speech Recognition Syst...
research
04/25/2022

Speech Detection For Child-Clinician Conversations In Danish For Low-Resource In-The-Wild Conditions: A Case Study

Use of speech models for automatic speech processing tasks can improve e...

Please sign up or login with your details

Forgot password? Click here to reset