Icassp 2022 Deep Noise Suppression Challenge

By Chandan K. A. Reddy, Harishchandra Dubey, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper, Robert Aichner, Sriram Srinivasan. 2022

237 citations recorded by the source corpus.

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. This is the 4th DNS challenge, with the previous editions held at INTERSPEECH 2020 [1], ICASSP 2021 [2], and INTERSPEECH 2021 [3]. We open-source datasets and test sets for researchers to train their deep noise suppression models, as well as a subjective evaluation framework based on ITU-T P.835 to rate and rank-order the challenge entries. We provide access to DNS-MOS P.835 and word accuracy (WAcc) APIs to challenge participants to help with iterative model improvements. In this challenge, we introduced the following changes: (i) Included mobile device scenarios in the blind test set; (ii) Included a personalized noise suppression track with baseline; (iii) Added WAcc as an objective metric; (iv) Included DNSMOS P.835; (v) Made the training datasets and test sets fullband (48 kHz). We use an average of WAcc and subjective scores P.835 SIG, BAK, and OVRL to get the final score for ranking the DNS models. We believe that as a research community, we still have a long way to go in achieving excellent speech quality in challenging noisy real-world scenarios.

Subfields: Artificial Intelligence, Biomedical Engineering, Speech & Audio, Signal Processing

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

In Biomedical Engineering

In Speech & Audio

In Signal Processing

Citations in the corpus

High Fidelity Neural Audio Compression (2022, background): “The ground truth is 16bits 24kHz wave. speech segments from DNS Challenge 4 (Dubey et al., 2022) and the Common Voice dataset (Ardila et al., 2019).”
High-Fidelity Audio Compression with Improved RVQGAN (2023, methodology): “Therefore, we use mel bin sizes [5, 10, 20, 40, 80, 160, 320] corresponding to the above filter lengths which were verified to be correct by manual inspection.”
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis (2023, methodology): “To align with EnCodec, we scale down Vocos to match its parameter count (7.9M) and train it on clean speech segments sourced from the DNS Challenge (Dubey et al., 2022).”
FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement (2022, unknown): “Our submission to the ICASSP 2022 Deep Noise Suppression (DNS) challenge (DNS-2022) [13] ranked overall 2nd place for the real-time fullband nono-personalized track in terms of Mean Opinion Score (MOS) and Word Accuracy (WAcc).”
ICASSP 2023 Deep Noise Suppression Challenge (2023, methodology): “Deep Speech Enhancement (DSE) models perform signiﬁcantly better than their classical counterparts [1–6].”
ICASSP 2022 Acoustic Echo Cancellation Challenge (2022, methodology): “The 1st place model [26] also won the ICASSP 2022 DNS Challenge [27], providing the only model that didn’t induce SIG [28] distortion in that challenge.”
Harmonic Gated Compensation Network Plus for ICASSP 2022 DNS Challenge (2022, methodology): “In DNS-2022, ITU-T P.835 framework [26] and Word Accuracy (WAcc) are used to evaluate the speech quality, and HGCN+ outperforms the baseline [2] with less parameters in all metrics, as shown in Table 3.”