ViSQOL: The Virtual Speech Quality Objective Listener

75 citations recorded by the source corpus.

How researchers see this paper

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

SoundStream: An End-to-End Neural Audio Codec (2021, positive): “We choose the freely available and recently open-sourced ViSQOL [56], [57] metric, which has previously shown comparable performance to POLQA.”
High Fidelity Neural Audio Compression (2022, methodology): “For objective metrics, we use ViSQOL (Hines et al., 2012; Chinen et al., 2020) 2 , together with the Scale-Invariant Signal-to-Noise Ration (SI-SNR) (Luo & Mesgarani, 2019; Nachmani et al., 2020; Chazan et al., 2021).”
ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric (2020, methodology): “The ViSQOL algorithms described in [7] and [8] share many components by design, such as the gammatone spectrogram and NSIM calculation.”
An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation (2020, background): “ViSQOL [93], [94] 2012 Specifically designed for voice over [55], [183] IP transmission”
Robustness of speech quality metrics to background noise and network degradations: Comparing ViSQOL, PESQ and POLQA (2013, unknown): “3697978-1-4799-0356-6/13/$31.00 ©2013 IEEE ICASSP 2013”
SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models (2023, methodology): “Objective Metrics We use ViSQOL metrics (Hines et al., 2012) to measure the speech quality.”