NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

By Gabriel Mittag, Babak Naderi, Assmaa Chehadi, Sebastian Möller. Interspeech, 2021

509 citations recorded by the source corpus.

In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the time-dependency modelling and time-pooling is achieved through a Self-Attention mechanism. Besides overall speech quality, the model also predicts the four speech quality dimensions Noisiness, Coloration, Discontinuity, and Loudness, and in this way gives more insight into the cause of a quality degradation. Furthermore, new datasets with over 13,000 speech files were created for training and validation of the model. The model was finally tested on a new, live-talking test dataset that contains recordings of real telephone calls. Overall, NISQA was trained and evaluated on 81 datasets from different sources and showed to provide reliable predictions also for unknown speech samples. The code, model weights, and datasets are open-sourced.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ac4106969f1188a2d0bcb09d2f5b237b53719a00

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ke Tan
2. Xiaohui Zhang
3. Zhaoheng Ni
4. Anurag Kumar

In Signal Processing

1. Ke Tan
2. Anurag Kumar

Citations in the corpus

• Torchaudio-Squim: Reference-Less Speech Quality and Intelligibility Measures in Torchaudio (2023, methodology): “Unlike more common approaches (e.g DNSMOS [9], NISQA [6]) which attempt to directly estimate MOS from a given sample, NORESQA-MOS relies on the idea of using non-matching references for a more grounded estimation [24].”