Unsupervised Uncertainty Measures Of Automatic Speech Recognition For Non-intrusive Speech Intelligibility Prediction

Abstract

Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth intelligibility labels or clean reference signals for supervised learning. In this work, we leverage an unsupervised uncertainty estimation method for predicting speech intelligibility, which does not require intelligibility labels or reference signals to train the predictor. Our experiments demonstrate that the uncertainty from state-of-the-art end-to-end automatic speech recognition (ASR) models is highly correlated with speech intelligibility. The proposed method is evaluated on two databases and the results show that the unsupervised uncertainty measures of ASR models are more correlated with speech intelligibility from listening results than the predictions made by widely used intrusive methods.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keytu2022unsupervised

Related papers

• An Evaluation Of Word-level Confidence Estimation For End-to-end Automatic Speech Recognition (2021)0.00
• An Attention Long Short-term Memory Based System For Automatic Classification Of Speech Intelligibility (2024)12.33
• Towards Unsupervised Speech Recognition Without Pronunciation Models (2024)0.00
• Uncertainty As A Predictor: Leveraging Self-supervised Learning For Zero-shot MOS Prediction (2023)6.34
• NIESR: Nuisance Invariant End-to-end Speech Recognition (2019)4.52
• Stoi-net: A Deep Learning Based Non-intrusive Speech Intelligibility Assessment Model (2020)0.00
• An Improved Uncertainty Propagation Method For Robust I-vector Based Speaker Recognition (2019)5.84
• A Reference-less Quality Metric For Automatic Speech Recognition Via Contrastive-learning Of A Multi-language Model With Self-supervision (2023)2.51