# MTI-Net: A Multi-Target Speech Intelligibility Prediction Model

arXiv: https://arxiv.org/abs/2204.03310 · HTML: https://mlsanity.com/paper/2204.03310/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding](https://mlsanity.com/paper/2111.02735/) (2021)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [Audio Self-supervised Learning: A Survey](https://mlsanity.com/paper/2203.01205/) (2022)
- [LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech](https://mlsanity.com/paper/2104.11462/) (2021)
- [The Zero Resource Speech Challenge 2021: Spoken language modelling](https://mlsanity.com/paper/2104.14700/) (2021)
- [Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM](https://mlsanity.com/paper/1808.05344/) (2018)
- [MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network](https://mlsanity.com/paper/2103.00110/) (2021)
- [Investigating self-supervised learning for speech enhancement and separation](https://mlsanity.com/paper/2203.07960/) (2022)
- [T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancement](https://mlsanity.com/paper/1910.06762/) (2019)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [Raw Waveform-based Speech Enhancement by Fully Convolutional Networks](https://mlsanity.com/paper/1703.02205/) (2017)
- [STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model](https://mlsanity.com/paper/2011.04292/) (2020)
- [NORESQA: A Framework for Speech Quality Assessment using Non-Matching References](https://mlsanity.com/paper/2109.08125/) (2021)
- [HASA-net: A non-intrusive hearing-aid speech assessment network](https://mlsanity.com/paper/2111.05691/) (2021)

## Built on by (most cited first, 6 of 6)

- [MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarios](https://mlsanity.com/paper/2308.12490/) (2023)
- [Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata](https://mlsanity.com/paper/2309.09548/) (2023)
- [Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Text](https://mlsanity.com/paper/2310.08225/) (2023)
- [Unsupervised speech intelligibility assessment with utterance level alignment distance between teacher and learner Wav2Vec-2.0 representations](https://mlsanity.com/paper/2306.08845/) (2023)
- [No Audiogram: Leveraging Existing Scores for Personalized Speech Intelligibility Prediction](https://mlsanity.com/paper/2506.02039/) (2025)
- [Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction](https://mlsanity.com/paper/2602.15484/) (2026)

## Abstract (arXiv)

Recently, deep learning (DL)-based non-intrusive speech assessment models have attracted great attention. Many studies report that these DL-based models yield satisfactory assessment performance and good flexibility, but their performance in unseen environments remains a challenge. Furthermore, compared to quality scores, fewer studies elaborate deep learning models to estimate intelligibility scores. This study proposes a multi-task speech intelligibility prediction model, called MTI-Net, for simultaneously predicting human and machine intelligibility measures. Specifically, given a speech utterance, MTI-Net is designed to predict human subjective listening test results and word error rate (WER) scores. We also investigate several methods that can improve the prediction performance of MTI-Net. First, we compare different features (including low-level features and embeddings from self-supervised learning (SSL) models) and prediction targets of MTI-Net. Second, we explore the effect of transfer learning and multi-tasking learning on training MTI-Net. Finally, we examine the potential advantages of fine-tuning SSL embeddings. Experimental results demonstrate the effectiveness of using cross-domain features, multi-task learning, and fine-tuning SSL embeddings. Furthermore, it is confirmed that the intelligibility and WER scores predicted by MTI-Net are highly correlated with the ground-truth scores.