In recent years, the introduction of neural networks (NNs) into the field of speech enhancement has brought significant improvements. However, many of the proposed methods are quite demanding in terms of computational complexity and memory footprint. For the application in dedicated communication devices, such as speakerphones, hands-free car systems, or smartphones, efficiency plays a major role along with performance. In this context, we present an efficient, high-performance hybrid joint acoustic echo control and noise suppression system, whereby our main contribution is the postfilter NN, performing both noise and residual echo suppression. The preservation of nearend speech is improved by a Bark-scale auditory filterbank for the NN postfilter. The proposed hybrid method is benchmarked with state-of-the-art methods and its effectiveness is demonstrated on the ICASSP 2023 AEC Challenge blind test set. We demonstrate that it offers high-quality nearend speech preservation during both double-talk and nearend speech conditions. At the same time, it is capable of efficient removal of echo leaks, achieving a comparable performance to already small state-of-the-art models such as the end-to-end DeepVQE-S, while requiring only around 10 % of its computational complexity. This makes it easily realtime implementable on a speakerphone device.
When models, e.g., for semantic segmentation, are applied to images that are vastly different from training data, the performance will drop significantly. Domain adaptation methods try to overcome this issue, but need samples from the target domain. However, this might not always be feasible for various reasons and therefore domain generalization methods are useful as they do not require any target data. We present a new diffusion-based domain extension (DIDEX) method and employ a diffusion model to generate a pseudo-target domain with diverse text prompts. In contrast to existing methods, this allows to control the style and content of the generated images and to introduce a high diversity. In a second step, we train a generalizing model by adapting towards this pseudo-target domain. We outperform previous approaches by a large margin across various datasets and architectures without using any real data. For the generalization from GTA5, we improve state-of-the-art mIoU performance by 3.8% absolute on average and for SYNTHIA by 11.8% absolute, marking a big step for the generalization performance on these benchmarks. Code is available at https://github.com/JNiemeijer/DIDEX
Most deep noise suppression (DNS) models are trained with reference-based losses requiring access to clean speech. However, sometimes an additive microphone model is insufficient for real-world applications. Accordingly, ways to use real training data in supervised learning for DNS models promise to reduce a potential training/inference mismatch. Employing real data for DNS training requires either generative approaches or a reference-free loss without access to the corresponding clean speech. In this work, we propose to employ an end-to-end non-intrusive deep neural network (DNN), named PESQ-DNN, to estimate perceptual evaluation of speech quality (PESQ) scores of enhanced real data. It provides a reference-free perceptual loss for employing real data during DNS training, maximizing the PESQ scores. Furthermore, we use an epoch-wise alternating training protocol, updating the DNS model on real data, followed by PESQ-DNN updating on synthetic data. The DNS model trained with the PESQ-DNN employing real data outperforms all reference methods employing only synthetic training data. On synthetic test data, our proposed method excels the Interspeech 2021 DNS Challenge baseline by a significant 0.32 PESQ points. Both on synthetic and real test data, the proposed method beats the baseline by 0.05 DNSMOS points - although PESQ-DNN optimizes for a different perceptual metric.
The task of semantic segmentation requires a model to assign semantic labels to each pixel of an image. However, the performance of such models degrades when deployed in an unseen domain with different data distributions compared to the training domain. We present a new augmentation-driven approach to domain generalization for semantic segmentation using a re-parameterized vision transformer (ReVT) with weight averaging of multiple models after training. We evaluate our approach on several benchmark datasets and achieve state-of-the-art mIoU performance of 47.3% (prior art: 46.3%) for small models and of 50.1% (prior art: 47.8%) for midsized models on commonly used benchmark datasets. At the same time, our method requires fewer parameters and reaches a higher frame rate than the best prior art. It is also easy to implement and, unlike network ensembles, does not add any computational complexity during inference.
The topic of deep acoustic echo control (DAEC) has seen many approaches with various model topologies in recent years. Convolutional recurrent networks (CRNs), consisting of a convolutional encoder and decoder encompassing a recurrent bottleneck, are repeatedly employed due to their ability to preserve nearend speech even in double-talk (DT) condition. However, past architectures are either computationally complex or trade off smaller model sizes with a decrease in performance. We propose an improved CRN topology which, compared to other realizations of this class of architectures, not only saves parameters and computational complexity, but also shows improved performance in DT, outperforming both baseline architectures FCRN and CRUSE. Striving for a condition-aware training, we also demonstrate the importance of a high proportion of double-talk and the missing value of nearend-only speech in DAEC training data. Finally, we show how to control the trade-off between aggressive echo suppression and near-end speech preservation by fine-tuning with condition-aware component loss functions.
Fully convolutional recurrent neural networks (FCRNs) have shown state-of-the-art performance in single-channel speech enhancement. However, the number of parameters and the FLOPs/second of the original FCRN are restrictively high. A further important class of efficient networks is the CRUSE topology, serving as reference in our work. By applying a number of topological changes at once, we propose both an efficient FCRN (FCRN15), and a new family of efficient convolutional recurrent neural networks (EffCRN23, EffCRN23lite). We show that our FCRN15 (875K parameters) and EffCRN23lite (396K) outperform the already efficient CRUSE5 (85M) and CRUSE4 (7.2M) networks, respectively, w.r.t. PESQ, DNSMOS and DeltaSNR, while requiring about 94% less parameters and about 20% less #FLOPs/frame. Thereby, according to these metrics, the FCRN/EffCRN class of networks provides new best-in-class network topologies for speech enhancement.
Deep neural networks (DNNs) have proven their capabilities in many areas in the past years, such as robotics, or automated driving, enabling technological breakthroughs. DNNs play a significant role in environment perception for the challenging application of automated driving and are employed for tasks such as detection, semantic segmentation, and sensor fusion. Despite this progress and tremendous research efforts, several issues still need to be addressed that limit the applicability of DNNs in automated driving. The bad generalization of DNNs to new, unseen domains is a major problem on the way to a safe, large-scale application, because manual annotation of new domains is costly, particularly for semantic segmentation. For this reason, methods are required to adapt DNNs to new domains without labeling effort. The task, which these methods aim to solve is termed unsupervised domain adaptation (UDA). While several different domain shifts can challenge DNNs, the shift between synthetic and real data is of particular importance for automated driving, as it allows the use of simulation environments for DNN training. In this work, we present an overview of the current state of the art in this field of research. We categorize and explain the different approaches for UDA. The number of considered publications is larger than any other survey on this topic. The scope of this survey goes far beyond the description of the UDA state-of-the-art. Based on our large data and knowledge base, we present a quantitative comparison of the approaches and use the observations to point out the latest trends in this field. In the following, we conduct a critical analysis of the state-of-the-art and highlight promising future research directions. With this survey, we aim to facilitate UDA research further and encourage scientists to exploit novel research directions to generalize DNNs better.
Wideband codecs such as AMR-WB or EVS are widely used in (mobile) speech communication. Evaluation of coded speech quality is often performed subjectively by an absolute category rating (ACR) listening test. However, the ACR test is impractical for online monitoring of speech communication networks. Perceptual evaluation of speech quality (PESQ) is one of the widely used metrics instrumentally predicting the results of an ACR test. However, the PESQ algorithm requires an original reference signal, which is usually unavailable in network monitoring, thus limiting its applicability. NISQA is a new non-intrusive neural-network-based speech quality measure, focusing on super-wideband speech signals. In this work, however, we aim at predicting the well-known PESQ metric using a non-intrusive PESQ-DNN model. We illustrate the potential of this model by predicting the PESQ scores of wideband-coded speech obtained from AMR-WB or EVS codecs operating at different bitrates in noisy, tandeming, and error-prone transmission conditions. We compare our methods with the state-of-the-art network topologies of QualityNet, WaweNet, and DNSMOS -- all applied to PESQ prediction -- by measuring the mean absolute error (MAE) and the linear correlation coefficient (LCC). The proposed PESQ-DNN offers the best total MAE and LCC of 0.11 and 0.92, respectively, in conditions without frame loss, and still is best when including frame loss. Note that our model could be similarly used to non-intrusively predict POLQA or other (intrusive) metrics. Upon article acceptance, code will be provided at GitHub.
The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive transformer decoder complicating the integration of external language models. In this paper, we explore relaxed attention, a simple and easy-to-implement smoothing of the attention weights, yielding a two-fold improvement to the general transformer architecture: First, relaxed attention provides regularization when applied to the self-attention layers in the encoder. Second, we show that it naturally supports the integration of an external language model as it suppresses the implicitly learned internal language model by relaxing the cross attention in the decoder. We demonstrate the benefit of relaxed attention across several tasks with clear improvement in combination with recent benchmark approaches. Specifically, we exceed the former state-of-the-art performance of 26.90% word error rate on the largest public lip-reading LRS3 benchmark with a word error rate of 26.31%, as well as we achieve a top-performing BLEU score of 37.67 on the IWSLT14 (DE$\rightarrow$EN) machine translation task without external language models and virtually no additional model parameters. Code and models will be made publicly available.
The emergence of data-driven machine learning (ML) has facilitated significant progress in many complicated tasks such as highly-automated driving. While much effort is put into improving the ML models and learning algorithms in such applications, little focus is put into how the training data and/or validation setting should be designed. In this paper we investigate the influence of several data design choices regarding training and validation of deep driving models trainable in an end-to-end fashion. Specifically, (i) we investigate how the amount of training data influences the final driving performance, and which performance limitations are induced through currently used mechanisms to generate training data. (ii) Further, we show by correlation analysis, which validation design enables the driving performance measured during validation to generalize well to unknown test environments. (iii) Finally, we investigate the effect of random seeding and non-determinism, giving insights which reported improvements can be deemed significant. Our evaluations using the popular CARLA simulator provide recommendations regarding data generation and driving route selection for an efficient future development of end-to-end driving models.