Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed using EER metric) for imposter identification in unseen speaker recognition and then introduce a robust speaker-specific thresholding technique for better performance. Secondly, inspired by the recent use of meta-learning techniques in speaker verification, we propose an end-to-end meta-learning framework for imposter detection which decouples the problem of imposter detection from unseen speaker identification. Thus, unlike most prior works that use some heuristics to detect imposters, the proposed network learns to detect imposters by leveraging the utterances of the enrolled speakers. Furthermore, we show the efficacy of the proposed techniques on VoxCeleb1, VCTK and the FFSVC 2022 datasets, beating the baselines by up to 10%.

Current adversarial attacks against speaker recognition systems (SRSs) require either white-box access or heavy black-box queries to the target SRS, thus still falling behind practical attacks against proprietary commercial APIs and voice-controlled devices. To fill this gap, we propose QFA2SR, an effective and imperceptible query-free black-box attack, by leveraging the transferability of adversarial voices. To improve transferability, we present three novel methods, tailored loss functions, SRS ensemble, and time-freq corrosion. The first one tailors loss functions to different attack scenarios. The latter two augment surrogate SRSs in two different ways. SRS ensemble combines diverse surrogate SRSs with new strategies, amenable to the unique scoring characteristics of SRSs. Time-freq corrosion augments surrogate SRSs by incorporating well-designed time-/frequency-domain modification functions, which simulate and approximate the decision boundary of the target SRS and distortions introduced during over-the-air attacks. QFA2SR boosts the targeted transferability by 20.9%-70.7% on four popular commercial APIs (Microsoft Azure, iFlytek, Jingdong, and TalentedSoft), significantly outperforming existing attacks in query-free setting, with negligible effect on the imperceptibility. QFA2SR is also highly effective when launched over the air against three wide-spread voice assistants (Google Assistant, Apple Siri, and TMall Genie) with 60%, 46%, and 70% targeted transferability, respectively.

This report describes the UNISOUND submission for Track1 and Track2 of VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC 2023). We submit the same system on Track 1 and Track 2, which is trained with only VoxCeleb2-dev. Large-scale ResNet and RepVGG architectures are developed for the challenge. We propose a consistency-aware score calibration method, which leverages the stability of audio voiceprints in similarity score by a Consistency Measure Factor (CMF). CMF brings a huge performance boost in this challenge. Our final system is a fusion of six models and achieves the first place in Track 1 and second place in Track 2 of VoxSRC 2023. The minDCF of our submission is 0.0855 and the EER is 1.5880%.

This technical report describes ChinaTelecom system for Track 1 (closed) of the VoxCeleb2023 Speaker Recognition Challenge (VoxSRC 2023). Our system consists of several ResNet variants trained only on VoxCeleb2, which were fused for better performance later. Score calibration was also applied for each variant and the fused system. The final submission achieved minDCF of 0.1066 and EER of 1.980%.

Despite its broad practical applications such as in fraud prevention, open-set speaker identification (OSI) has received less attention in the speaker recognition community compared to speaker verification (SV). OSI deals with determining if a test speech sample belongs to a speaker from a set of pre-enrolled individuals (in-set) or if it is from an out-of-set speaker. In addition to the typical challenges associated with speech variability, OSI is prone to the "false-alarm problem"; as the size of the in-set speaker population (a.k.a watchlist) grows, the out-of-set scores become larger, leading to increased false alarm rates. This is in particular challenging for applications in financial institutions and border security where the watchlist size is typically of the order of several thousand speakers. Therefore, it is important to systematically quantify the false-alarm problem, and develop techniques that alleviate the impact of watchlist size on detection performance. Prior studies on this problem are sparse, and lack a common benchmark for systematic evaluations. In this paper, we present the first public benchmark for OSI, developed using the VoxCeleb dataset. We quantify the effect of the watchlist size and speech duration on the watchlist-based speaker detection task using three strong neural network based systems. In contrast to the findings from prior research, we show that the commonly adopted adaptive score normalization is not guaranteed to improve the performance for this task. On the other hand, we show that score calibration and score fusion, two other commonly used techniques in SV, result in significant improvements in OSI performance.

A new classifier is presented for text-independent speaker recognition. The new classifier is called the modified neural tree network (MNTN). The NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. The MNTN differs from the stan(cid:173) dard NTN in that a new learning rule based on discriminant learning is used, which minimizes the classification error as opposed to a norm of the approximation error. The MNTN also uses leaf probability mea(cid:173) sures in addition to the class labels.

A novel approach for comparing sequences of observations using an explicit-expansion kernel is demonstrated. The kernel is derived using the assumption of the independence of the sequence of observations and a mean-squared error training criterion. The use of an explicit expan- sion kernel reduces classifier model size and computation dramatically, resulting in model sizes and computation one-hundred times smaller in our application. The explicit expansion also preserves the computational advantages of an earlier architecture based on mean-squared error train- ing. Training using standard support vector machine methodology gives accuracy that significantly exceeds the performance of state-of-the-art mean-squared error training for a speaker recognition task.

The protected With the ubiquity of smart devices that use speaker recognition (SR) groups in this study are defined as'gender' and'nationality' systems as a means of authenticating individuals and personalizing of speakers. The VoxCeleb dataset [4] is used in this study given their services, fairness of SR systems has becomes an important that it is the most widely used dataset in training SR systems and the point of focus. In this paper we study the notion of fairness in recent wide range of diversity among its speakers. SR systems based on 3 popular and relevant definitions, namely Statistical In summary we make the following contributions: (1) We evaluate Parity, Equalized Odds, and Equal Opportunity. We examine fairness of the current widely used architectures in SR and crossexamine 5 popular neural architectures and 5 commonly used loss functions them with different loss functions used in training.

This paper summarises the findings from the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22), which was held in conjunction with INTERSPEECH 2022. The goal of this challenge was to evaluate how well state-of-the-art speaker recognition systems can diarise and recognise speakers from speech obtained "in the wild". The challenge consisted of: (i) the provision of publicly available speaker recognition and diarisation data from YouTube videos together with ground truth annotation and standardised evaluation software; and (ii) a public challenge and hybrid workshop held at INTERSPEECH 2022. We describe the four tracks of our challenge along with the baselines, methods, and results. We conclude with a discussion on the new domain-transfer focus of VoxSRC-22, and on the progression of the challenge from the previous three editions.

This work considers training neural networks for speaker recognition with a much smaller dataset size compared to contemporary work. We artificially restrict the amount of data by proposing three subsets of the popular VoxCeleb2 dataset. These subsets are restricted to 50\,k audio files (versus over 1\,M files available), and vary on the axis of number of speakers and session variability. We train three speaker recognition systems on these subsets; the X-vector, ECAPA-TDNN, and wav2vec2 network architectures. We show that the self-supervised, pre-trained weights of wav2vec2 substantially improve performance when training data is limited. Code and data subsets are available at https://github.com/nikvaessen/w2v2-speaker-few-samples.