Improving Speech Enhancement through Fine-Grained Speech Characteristics

While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and can sound unnatural. We propose a novel approach to speech enhancement aimed at improving perceptual quality and naturalness of enhanced signals by optimizing for key characteristics of speech. We first identify key acoustic parameters that have been found to correlate well with voice quality (e.g. jitter, shimmer, and spectral flux) and then propose objective functions which are aimed at reducing the difference between clean speech and enhanced speech with respect to these features. The full set of acoustic features is the extended Geneva Acoustic Parameter Set (eGeMAPS), which includes 25 different attributes associated with perception of speech. Given the non-differentiable nature of these feature computation, we first build differentiable estimators of the eGeMAPS and then use them to fine-tune existing speech enhancement systems. Our approach is generic and can be applied to any existing deep learning based enhancement systems to further improve the enhanced speech signals. Experimental results conducted on the Deep Noise Suppression (DNS) Challenge dataset shows that our approach can improve the state-of-the-art deep learning based enhancement systems.

Self-supervision and Learnable STRFs for Age, Emotion, and Country Prediction

This work presents a multitask approach to the simultaneous estimation of age, country of origin, and emotion given vocal burst audio for the 2022 ICML Expressive Vocalizations Challenge ExVo-MultiTask track. The method of choice utilized a combination of spectro-temporal modulation and self-supervised features, followed by an encoder-decoder network organized in a multitask paradigm. We evaluate the complementarity between the tasks posed by examining independent task-specific and joint models, and explore the relative strengths of different feature sets. We also introduce a simple score fusion mechanism to leverage the complementarity of different feature sets for this task. We find that robust data preprocessing in conjunction with score fusion over spectro-temporal receptive field and HuBERT models achieved our best ExVo-MultiTask test score of 0.412.

Towards End-to-End Private Automatic Speaker Recognition

The development of privacy-preserving automatic speaker verification systems has been the focus of a number of studies with the intent of allowing users to authenticate themselves without risking the privacy of their voice. However, current privacy-preserving methods assume that the template voice representations (or speaker embeddings) used for authentication are extracted locally by the user. This poses two important issues: first, knowledge of the speaker embedding extraction model may create security and robustness liabilities for the authentication system, as this knowledge might help attackers in crafting adversarial examples able to mislead the system; second, from the point of view of a service provider the speaker embedding extraction model is arguably one of the most valuable components in the system and, as such, disclosing it would be highly undesirable. In this work, we show how speaker embeddings can be extracted while keeping both the speaker's voice and the service provider's model private, using Secure Multiparty Computation. Further, we show that it is possible to obtain reasonable trade-offs between security and computational cost. This work is complementary to those showing how authentication may be performed privately, and thus can be considered as another step towards fully private automatic speaker recognition.

Bear the Query in Mind: Visual Grounding with Query-conditioned Convolution

Visual grounding is a task that aims to locate a target object according to a natural language expression. As a multi-modal task, feature interaction between textual and visual inputs is vital. However, previous solutions mainly handle each modality independently before fusing them together, which does not take full advantage of relevant textual information while extracting visual features. To better leverage the textual-visual relationship in visual grounding, we propose a Query-conditioned Convolution Module (QCM) that extracts query-aware visual features by incorporating query information into the generation of convolutional kernels. With our proposed QCM, the downstream fusion module receives visual features that are more discriminative and focused on the desired object described in the expression, leading to more accurate predictions. Extensive experiments on three popular visual grounding datasets demonstrate that our method achieves state-of-the-art performance. In addition, the query-aware visual features are informative enough to achieve comparable performance to the latest methods when directly used for prediction without further multi-modal fusion.

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

Pseudo labeling and consistency regularization approaches with confidence-based thresholding have made great progress in semi-supervised learning (SSL). In this paper, we theoretically and empirically analyze the relationship between the unlabeled data distribution and the desirable confidence threshold. Our analysis shows that previous methods might fail to define favorable threshold since they either require a pre-defined / fixed threshold or an ad-hoc threshold adjusting scheme that does not reflect the learning effect well, resulting in inferior performance and slow convergence, especially for complicated unlabeled data distributions. We hence propose \emph{FreeMatch} to define and adjust the confidence threshold in a self-adaptive manner according to the model's learning status. To handle complicated unlabeled data distributions more effectively, we further propose a self-adaptive class fairness regularization method that encourages the model to produce diverse predictions during training. Extensive experimental results indicate the superiority of FreeMatch especially when the labeled data are extremely rare. FreeMatch achieves \textbf{5.78}\%, \textbf{13.59}\%, and \textbf{1.28}\% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class, STL-10 with 4 labels per class, and ImageNet with 100k labels respectively.

On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice

Lately, there has been a global effort by multiple research groups to detect COVID-19 from voice. Different researchers use different kinds of information from the voice signal to achieve this. Various types of phonated sounds and the sound of cough and breath have all been used with varying degrees of success in automated voice-based COVID-19 detection apps. In this paper, we show that detecting COVID-19 from voice does not require custom-made non-standard features or complicated neural network classifiers rather it can be successfully done with just standard features and simple binary classifiers. In fact, we show that the latter is not only more accurate and interpretable and also more computationally efficient in that they can be run locally on small devices. We demonstrate this from a human-curated dataset collected and calibrated in clinical settings. On this dataset which comprises over 1000 speakers, a simple binary classifier is able to achieve 94% detection accuracy.

Recent improvements of ASR models in the face of adversarial attacks

Like many other tasks involving neural networks, Speech Recognition models are vulnerable to adversarial attacks. However recent research has pointed out differences between attacks and defenses on ASR models compared to image models. Improving the robustness of ASR models requires a paradigm shift from evaluating attacks on one or a few models to a systemic approach in evaluation. We lay the ground for such research by evaluating on various architectures a representative set of adversarial attacks: targeted and untargeted, optimization and speech processing-based, white-box, black-box and targeted attacks. Our results show that the relative strengths of different attack algorithms vary considerably when changing the model architecture, and that the results of some attacks are not to be blindly trusted. They also indicate that training choices such as self-supervised pretraining can significantly impact robustness by enabling transferable perturbations. We release our source code as a package that should help future research in evaluating their attacks and defenses.

HEAR 2021: Holistic Evaluation of Audio Representations

What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR 2021 NeurIPS challenge is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. HEAR 2021 evaluates audio representations using a benchmark suite across a variety of domains, including speech, environmental sound, and music. In the spirit of shared exchange, each participant submitted an audio embedding model following a common API that is general-purpose, open-source, and freely available to use. Twenty-nine models by thirteen external teams were evaluated on nineteen diverse downstream tasks derived from sixteen datasets. Open evaluation code, submitted models and datasets are key contributions, enabling comprehensive and reproducible evaluation, as well as previously impossible longitudinal studies. It still remains an open question whether one single general-purpose audio representation can perform as holistically as the human ear.

Point3D: tracking actions as moving points with 3D CNNs

Spatio-temporal action recognition has been a challenging task that involves detecting where and when actions occur. Current state-of-the-art action detectors are mostly anchor-based, requiring sensitive anchor designs and huge computations due to calculating large numbers of anchor boxes. Motivated by nascent anchor-free approaches, we propose Point3D, a flexible and computationally efficient network with high precision for spatio-temporal action recognition. Our Point3D consists of a Point Head for action localization and a 3D Head for action classification. Firstly, Point Head is used to track center points and knot key points of humans to localize the bounding box of an action. These location features are then piped into a time-wise attention to learn long-range dependencies across frames. The 3D Head is later deployed for the final action classification. Our Point3D achieves state-of-the-art performance on the JHMDB, UCF101-24, and AVA benchmarks in terms of frame-mAP and video-mAP. Comprehensive ablation studies also demonstrate the effectiveness of each module proposed in our Point3D.