Improving pronunciation assessment via ordinal regression with anchored reference samples

10/26/2020
by   Bin Su, et al.
0

Sentence level pronunciation assessment is important for Computer Assisted Language Learning (CALL). Traditional speech pronunciation assessment, based on the Goodness of Pronunciation (GOP) algorithm, has some weakness in assessing a speech utterance: 1) Phoneme GOP scores cannot be easily translated into a sentence score with a simple average for effective assessment; 2) The rank ordering information has not been well exploited in GOP scoring for delivering a robust assessment and correlate well with a human rater's evaluations. In this paper, we propose two new statistical features, average GOP (aGOP) and confusion GOP (cGOP) and use them to train a binary classifier in Ordinal Regression with Anchored Reference Samples (ORARS). When the proposed approach is tested on Microsoft mTutor ESL Dataset, a relative improvement of Pearson correlation coefficient of 26.9 one. The performance is at a human-parity level or better than human raters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2022

Ordinal Regression via Binary Preference vs Simple Regression: Statistical and Experimental Perspectives

Ordinal regression with anchored reference samples (ORARS) has been prop...
research
08/09/2023

Automatically measuring speech fluency in people with aphasia: first achievements using read-speech data

Background: Speech and language pathologists (SLPs) often relyon judgeme...
research
05/16/2020

Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models

Many applications of speech technology require more and more audio data....
research
05/31/2023

Zero-Shot Automatic Pronunciation Assessment

Automatic Pronunciation Assessment (APA) is vital for computer-assisted ...
research
05/29/2023

A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment

Automatic Pronunciation Assessment (APA) plays a vital role in Computer-...
research
10/03/2020

autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients

The Thrombolysis in Cerebral Infarction (TICI) score is an important met...
research
05/28/2023

Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification

This paper proposes an improved Goodness of Pronunciation (GoP) that uti...

Please sign up or login with your details

Forgot password? Click here to reset