For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is realized with the use of three Gaussian inference layers, each consisting of a learnable transition model that extracts distinct speech components. Notably, a strengthened transition model is specifically designed to model complex speech dynamics. We also propose a self-supervision method to dynamically disentangle content without the use of labels other than speaker identities. The efficacy of the proposed framework is validated via experiments conducted on the VoxCeleb and SITW datasets with 9.56% and 8.24% average reductions in EER and minDCF, respectively. Since neither additional model training nor data is specifically needed, it is easily applicable in practical use.

In this section, we will introduce the simplified method for implementing the proposed Gaussian inference. Similar to [9], we assume that the covariance (and precision) matrices are diagonal and choose to estimate directly the log-precision which turns out to be more convenient for following derivation. As the gain factor A is a diagonal matrix, and z and ϕ are vectors, the expensive matrix multiplication operations and numerically problematic matrix inversions are simplified into element-wise multiplication of diagonal elements and vectors. This is the same as the implementation of point-wise multiplication for matrices in neural networks and thus, is easy to implement based on existing toolkits. The method above can also be applied to layer 1 and layer 3 of the proposed RecXi.

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is realized with the use of three Gaussian inference layers, each consisting of a learnable transition model that extracts distinct speech components. Notably, a strengthened transition model is specifically designed to model complex speech dynamics. We also propose a self-supervision method to dynamically disentangle content without the use of labels other than speaker identities. The efficacy of the proposed framework is validated via experiments conducted on the VoxCeleb and SITW datasets with 9.56% and 8.24% average reductions in EER and minDCF, respectively. Since neither additional model training nor data is specifically needed, it is easily applicable in practical use.

Recent research in speaker recognition aims to address vulnerabilities due to variations between enrolment and test utterances, particularly in the multi-genre phenomenon where the utterances are in different speech genres. Previous resources for Vietnamese speaker recognition are either limited in size or do not focus on genre diversity, leaving studies in multi-genre effects unexplored. This paper introduces VoxVietnam, the first multi-genre dataset for Vietnamese speaker recognition with over 187,000 utterances from 1,406 speakers and an automated pipeline to construct a dataset on a large scale from public sources. Our experiments show the challenges posed by the multi-genre phenomenon to models trained on a single-genre dataset, and demonstrate a significant increase in performance upon incorporating the VoxVietnam into the training process. Our experiments are conducted to study the challenges of the multi-genre phenomenon in speaker recognition and the performance gain when the proposed dataset is used for multi-genre training.

The VoxCeleb Speaker Recognition Challenges (VoxSRC) were a series of challenges and workshops that ran annually from 2019 to 2023. The challenges primarily evaluated the tasks of speaker recognition and diarisation under various settings including: closed and open training data; as well as supervised, self-supervised, and semi-supervised training for domain adaptation. The challenges also provided publicly available training and evaluation datasets for each task and setting, with new test sets released each year. In this paper, we provide a review of these challenges that covers: what they explored; the methods developed by the challenge participants and how these evolved; and also the current state of the field for speaker verification and diarisation. We chart the progress in performance over the five installments of the challenge on a common evaluation dataset and provide a detailed analysis of how each year's special focus affected participants' performance. This paper is aimed both at researchers who want an overview of the speaker recognition and diarisation field, and also at challenge organisers who want to benefit from the successes and avoid the mistakes of the VoxSRC challenges. We end with a discussion of the current strengths of the field and open challenges. Project page : https://mm.kaist.ac.kr/datasets/voxceleb/voxsrc/workshop.html

Speaker recognition technology is applied in various tasks ranging from personal virtual assistants to secure access systems. However, the robustness of these systems against adversarial attacks, particularly to additive perturbations, remains a significant challenge. In this paper, we pioneer applying robustness certification techniques to speaker recognition, originally developed for the image domain. In our work, we cover this gap by transferring and improving randomized smoothing certification techniques against norm-bounded additive perturbations for classification and few-shot learning tasks to speaker recognition. We demonstrate the effectiveness of these methods on VoxCeleb 1 and 2 datasets for several models. We expect this work to improve voice-biometry robustness, establish a new certification benchmark, and accelerate research of certification methods in the audio domain.

Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings both offline for voice profiles extracted from enrollment utterances, and online from runtime utterances. Due to the distinct circumstances of enrollment and runtime, such as different computation and latency constraints, several applications would benefit from an asymmetric enrollment-verification framework that uses different models for enrollment and runtime embedding generation. To support this asymmetric SID where each of the two models can be updated independently, we propose using a lightweight neural network to map the embeddings from the two independent models to a shared speaker embedding space. Our results show that this approach significantly outperforms cosine scoring in a shared speaker logit space for models that were trained with a contrastive loss on large datasets with many speaker identities. This proposed Neural Embedding Speaker Space Alignment (NESSA) combined with an asymmetric update of only one of the models delivers at least 60% of the performance gain achieved by updating both models in the standard symmetric SID approach.

Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has focused on speaker recognition (SR), a promising voice-based biometric recognition technique. In this work, we propose SLMIA-SR, the first membership inference attack tailored to SR. In contrast to conventional example-level attack, our attack features speaker-level membership inference, i.e., determining if any voices of a given speaker, either the same as or different from the given inference voices, have been involved in the training of a model. It is particularly useful and practical since the training and inference voices are usually distinct, and it is also meaningful considering the open-set nature of SR, namely, the recognition speakers were often not present in the training data. We utilize intra-similarity and inter-dissimilarity, two training objectives of SR, to characterize the differences between training and non-training speakers and quantify them with two groups of features driven by carefully-established feature engineering to mount the attack. To improve the generalizability of our attack, we propose a novel mixing ratio training strategy to train attack models. To enhance the attack performance, we introduce voice chunk splitting to cope with the limited number of inference voices and propose to train attack models dependent on the number of inference voices. Our attack is versatile and can work in both white-box and black-box scenarios. Additionally, we propose two novel techniques to reduce the number of black-box queries while maintaining the attack performance. Extensive experiments demonstrate the effectiveness of SLMIA-SR.

Audio adversarial examples (AEs) have posed significant security challenges to real-world speaker recognition systems. Most black-box attacks still require certain information from the speaker recognition model to be effective (e.g., keeping probing and requiring the knowledge of similarity scores). This work aims to push the practicality of the black-box attacks by minimizing the attacker's knowledge about a target speaker recognition model. Although it is not feasible for an attacker to succeed with completely zero knowledge, we assume that the attacker only knows a short (or a few seconds) speech sample of a target speaker. Without any probing to gain further knowledge about the target model, we propose a new mechanism, called parrot training, to generate AEs against the target model. Motivated by recent advancements in voice conversion (VC), we propose to use the one short sentence knowledge to generate more synthetic speech samples that sound like the target speaker, called parrot speech. Then, we use these parrot speech samples to train a parrot-trained(PT) surrogate model for the attacker. Under a joint transferability and perception framework, we investigate different ways to generate AEs on the PT model (called PT-AEs) to ensure the PT-AEs can be generated with high transferability to a black-box target model with good human perceptual quality. Real-world experiments show that the resultant PT-AEs achieve the attack success rates of 45.8% - 80.8% against the open-source models in the digital-line scenario and 47.9% - 58.3% against smart devices, including Apple HomePod (Siri), Amazon Echo, and Google Home, in the over-the-air scenario.

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is realized with the use of three Gaussian inference layers, each consisting of a learnable transition model that extracts distinct speech components. Notably, a strengthened transition model is specifically designed to model complex speech dynamics. We also propose a self-supervision method to dynamically disentangle content without the use of labels other than speaker identities. The efficacy of the proposed framework is validated via experiments conducted on the VoxCeleb and SITW datasets with 9.56% and 8.24% average reductions in EER and minDCF, respectively. Since neither additional model training nor data is specifically needed, it is easily applicable in practical use.