# CORN: Co-Trained Full- And No-Reference Speech Quality Assessment

arXiv: https://arxiv.org/abs/2310.09388 · HTML: https://mlsanity.com/paper/2310.09388/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019)
- [Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks](https://mlsanity.com/paper/1904.03416/) (2019)
- [CDPAM: Contrastive learning for perceptual audio similarity](https://mlsanity.com/paper/2102.05109/) (2021)
- [HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks](https://mlsanity.com/paper/2006.05694/) (2020)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning](https://mlsanity.com/paper/1904.02616/) (2019)
- [A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences](https://mlsanity.com/paper/2001.04460/) (2020)
- [AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech](https://mlsanity.com/paper/1611.09207/) (2016)
- [SESQA: semi-supervised learning for speech quality assessment](https://mlsanity.com/paper/2010.00368/) (2020)
- [NORESQA: A Framework for Speech Quality Assessment using Non-Matching References](https://mlsanity.com/paper/2109.08125/) (2021)
- [A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition](https://mlsanity.com/paper/2007.00144/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework](https://mlsanity.com/paper/2001.08662/) (2020)
- [A Pyramid Recurrent Network for Predicting Crowdsourced Speech-Quality Ratings of Real-World Signals](https://mlsanity.com/paper/2007.15797/) (2020)
- [Audio Similarity is Unreliable as a Proxy for Audio Quality](https://mlsanity.com/paper/2206.13411/) (2022)

## Built on by (most cited first, 1 of 1)

- [Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings](https://mlsanity.com/paper/2509.03292/) (2025)

## Abstract (arXiv)

Perceptual evaluation constitutes a crucial aspect of various audio-processing tasks. Full reference (FR) or similarity-based metrics rely on high-quality reference recordings, to which lower-quality or corrupted versions of the recording may be compared for evaluation. In contrast, no-reference (NR) metrics evaluate a recording without relying on a reference. Both the FR and NR approaches exhibit advantages and drawbacks relative to each other. In this paper, we present a novel framework called CORN that amalgamates these dual approaches, concurrently training both FR and NR models together. After training, the models can be applied independently. We evaluate CORN by predicting several common objective metrics and across two different architectures. The NR model trained using CORN has access to a reference recording during training, and thus, as one would expect, it consistently outperforms baseline NR models trained independently. Perhaps even more remarkable is that the CORN FR model also outperforms its baseline counterpart, even though it relies on the same training data and the same model architecture. Thus, a single training regime produces two independently useful models, each outperforming independently trained models