Wawenets: A No-Reference Convolutional Waveform-Based Approach to Estimating Narrowband and Wideband Speech Quality

Catellier, Andrew; Voran, S.

doi:10.1109/icassp40776.2020.9054204

Cited by 31 publications

(44 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 presents the validation and test set results of the overall MOS prediction compared to the single-ended models P.563 [5], ANIQUE+ [36], WAWEnets [12], and the doubleended models POLQA [4], DIAL [37], and VISQOL (v3.1.0) [38] 3 . NISQA outperforms the other single-ended speech quality models on most of the datasets, except for the ITU-T Suppl.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Mittag¹,

Naderi²,

Chehadi³

et al. 2021

Interspeech 2021

107

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Recently, deep learning methods have been applied to build single-ended speech quality models [9][10][11][12][13][14][15][16][17] and showed to outperform traditional approaches without the need for a clean reference. In [18], we presented the deep learning model NISQA that predicts speech quality of super-wideband (SWB) speech samples.…”

Section: Introductionmentioning

confidence: 99%

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

Mittag¹,

Naderi²,

Chehadi³

et al. 2021

Interspeech 2021

107

View full text Add to dashboard Cite

show abstract

“…It has to be noted that WEnets PESQ operates without reference signal, so the task for this measure is significantly more difficult than for all other measures. The original work reports Pearson correlation of 0.97 with PESQ [63], where training and testing signals were speech items processed by different speech codecs followed by noise suppression. This type of material fits PESQ original domain, but not many of our experiments, where, e.g.…”

Section: Results For the Artifacts-only Scores For The Source Separat...mentioning

confidence: 99%

“…with the aim of making them completely or partially non-intrusive [61]- [64]. Of the referenced works, only [63] provides the trained DNNs [65], referred to as Waveform Evaluation Networks (WEnets). These are four DNNs, trained to predict PESQ, POLQA, PEMO-Q, or Short-Time Objective Intelligibility (STOI), without reference signals.…”

Section: O Methods Based On Deep Learningmentioning

confidence: 99%

Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence

Torcoli

Kastner

Herre

2021

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Over the past few decades, computational methods have been developed to estimate perceptual audio quality. These methods, also referred to as objective quality measures, are usually developed and intended for a specific application domain. Because of their convenience, they are often used outside their original intended domain, even if it is unclear whether they provide reliable quality estimates in this case. This work studies the correlation of well-known state-of-the-art objective measures with human perceptual scores in two different domains: audio coding and source separation. The following objective measures are considered: fwS-NRseg, dLLR, PESQ, PEAQ, POLQA, PEMO-Q, ViSQOLAudio, (SI-)BSSEval, PEASS, LKR-PI, 2f-model, and HAAQI. Additionally, a novel measure (SI-SA2f) is presented, based on the 2f-model and a BSSEval-based signal decomposition. We use perceptual scores from 7 listening tests about audio coding and 7 listening tests about source separation as ground-truth data for the correlation analysis. The results show that one method (2f-model) performs significantly better than the others on both domains and indicate that the dataset for training the method and a robust underlying auditory model are crucial factors towards a universal, domainindependent objective measure.

show abstract

“…Another possibility to relax supervision is through the prediction or generation of pseudo ground truth. Although it is tempting to calculate the loss through a no-reference speech quality prediction network [5], experiments have shown that DNNs might over-optimize one perceptual metric without necessarily improving others [6,7], let alone a prediction of them. Wang et al used a pair of generative adversarial networks to map speech signals from noisy to clean [8].…”

Section: Introductionmentioning

confidence: 99%

Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems

Xia¹,

Xu²,

Kumar³

2021

Preprint

View full text Add to dashboard Cite

Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the scenarios where such systems are used. In this paper, we explore methods that enable supervised speech enhancement systems to train on real-world degraded speech data. Specifically, we propose a semi-supervised approach for speech enhancement in which we first train a modified vector-quantized variational autoencoder that solves a source separation task. We then use this trained autoencoder to further train an enhancement network using real-world noisy speech data by computing a triplet-based unsupervised loss function. Experiments show promising results for incorporating real-world data in training speech enhancement systems.

show abstract

Wawenets: A No-Reference Convolutional Waveform-Based Approach to Estimating Narrowband and Wideband Speech Quality

Cited by 31 publications

References 16 publications

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

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

Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence

Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems

Contact Info

Product

Resources

About