Norefer: A Referenceless Quality Metric For Automatic Speech Recognition Via Semi-supervised Language Model Fine-tuning With Contrastive Learning

Abstract

This paper introduces NoRefER, a novel referenceless quality metric for automatic speech recognition (ASR) systems. Traditional reference-based metrics for evaluating ASR systems require costly ground-truth transcripts. NoRefER overcomes this limitation by fine-tuning a multilingual language model for pair-wise ranking ASR hypotheses using contrastive learning with Siamese network architecture. The self-supervised NoRefER exploits the known quality relationships between hypotheses from multiple compression levels of an ASR for learning to rank intra-sample hypotheses by quality, which is essential for model comparisons. The semi-supervised version also uses a referenced dataset to improve its inter-sample quality ranking, which is crucial for selecting potentially erroneous samples. The results indicate that NoRefER correlates highly with reference-based metrics and their intra-sample ranks, indicating a high potential for referenceless ASR evaluation or a/b testing.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyuksel2023norefer

Related papers

• A Reference-less Quality Metric For Automatic Speech Recognition Via Contrastive-learning Of A Multi-language Model With Self-supervision (2023)2.51
• Metricnet: Towards Improved Modeling For Non-intrusive Speech Quality Assessment (2021)0.00
• Evaluating User Perception Of Speech Recognition System Quality With Semantic Distance Metric (2021)6.77
• NOMAD: Unsupervised Learning Of Perceptual Embeddings For Speech Enhancement And Non-matching Reference Audio Quality Assessment (2023)7.50
• Quality-net: An End-to-end Non-intrusive Speech Quality Assessment Model Based On BLSTM (2018)15.62
• Full-reference Speech Quality Estimation With Attentional Siamese Neural Networks (2021)8.60
• Speechbertscore: Reference-aware Automatic Evaluation Of Speech Generation Leveraging NLP Evaluation Metrics (2024)10.74
• More For Less: Non-intrusive Speech Quality Assessment With Limited Annotations (2021)7.16