# STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model

arXiv: https://arxiv.org/abs/2011.04292 · HTML: https://mlsanity.com/paper/2011.04292/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 19 of 19)

- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids](https://mlsanity.com/paper/2204.03305/) (2022)
- [Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech](https://mlsanity.com/paper/2402.16321/) (2024)
- [MTI-Net: A Multi-Target Speech Intelligibility Prediction Model](https://mlsanity.com/paper/2204.03310/) (2022)
- [SVSNet: An End-to-end Speaker Voice Similarity Assessment Model](https://mlsanity.com/paper/2107.09392/) (2021)
- [HASA-net: A non-intrusive hearing-aid speech assessment network](https://mlsanity.com/paper/2111.05691/) (2021)
- [AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment](https://mlsanity.com/paper/2501.18314/) (2025)
- [NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing](https://mlsanity.com/paper/2502.12002/) (2025)
- [Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps](https://mlsanity.com/paper/2407.04578/) (2024)
- [Towards Intelligibility-Oriented Audio-Visual Speech Enhancement](https://mlsanity.com/paper/2111.09642/) (2021)
- [Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations](https://mlsanity.com/paper/2111.12531/) (2021)
- [Unsupervised speech intelligibility assessment with utterance level alignment distance between teacher and learner Wav2Vec-2.0 representations](https://mlsanity.com/paper/2306.08845/) (2023)
- [A Non-Intrusive Neural Quality Assessment Model for Surface Electromyography Signals](https://mlsanity.com/paper/2402.05482/) (2024)
- [LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning](https://mlsanity.com/paper/2509.25670/) (2025)
- [VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories](https://mlsanity.com/paper/2604.10542/) (2026)
- [CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment](https://mlsanity.com/paper/2211.02577/) (2022)
- [Capacity-Net-Based RIS Precoding Design without Channel Estimation for mmWave MIMO System](https://mlsanity.com/paper/2509.25660/) (2025)
- [Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction](https://mlsanity.com/paper/2602.15484/) (2026)
- [Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning](https://mlsanity.com/paper/2610.01012/) (2026)

## Abstract (arXiv)

The calculation of most objective speech intelligibility assessment metrics requires clean speech as a reference. Such a requirement may limit the applicability of these metrics in real-world scenarios. To overcome this limitation, we propose a deep learning-based non-intrusive speech intelligibility assessment model, namely STOI-Net. The input and output of STOI-Net are speech spectral features and predicted STOI scores, respectively. The model is formed by the combination of a convolutional neural network and bidirectional long short-term memory (CNN-BLSTM) architecture with a multiplicative attention mechanism. Experimental results show that the STOI score estimated by STOI-Net has a good correlation with the actual STOI score when tested with noisy and enhanced speech utterances. The correlation values are 0.97 and 0.83, respectively, for the seen test condition (the test speakers and noise types are involved in the training set) and the unseen test condition (the test speakers and noise types are not involved in the training set). The results confirm the capability of STOI-Net to accurately predict the STOI scores without referring to clean speech.