ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification

The accuracy of modern automatic speaker verification (ASV) systems, when trained exclusively on adult data, drops substantially when applied to children's speech. The scarcity of children's speech corpora hinders fine-tuning ASV systems for children's speech. Hence, there is a timely need to explore more effective ways of reusing adults' speech data. One promising approach is to align vocal-tract parameters between adults and children through children-specific data augmentation, referred here to as ChildAugment. Specifically, we modify the formant frequencies and formant bandwidths of adult speech to emulate children's speech. The modified spectra are used to train ECAPA-TDNN (emphasized channel attention, propagation, and aggregation in time-delay neural network) recognizer for children. We compare ChildAugment against various state-of-the-art data augmentation techniques for children's ASV. We also extensively compare different scoring methods, including cosine scoring, PLDA (probabilistic linear discriminant analysis), and NPLDA (neural PLDA). We also propose a low-complexity weighted cosine score for extremely low-resource children ASV. Our findings on the CSLU kids corpus indicate that ChildAugment holds promise as a simple, acoustics-motivated approach, for improving state-of-the-art deep learning based ASV for children. We achieve up to 12.45% (boys) and 11.96% (girls) relative improvement over the baseline.

Generalizing Speaker Verification for Spoof Awareness in the Embedding Space

It is now well-known that automatic speaker verification (ASV) systems can be spoofed using various types of adversaries. The usual approach to counteract ASV systems against such attacks is to develop a separate spoofing countermeasure (CM) module to classify speech input either as a bonafide, or a spoofed utterance. Nevertheless, such a design requires additional computation and utilization efforts at the authentication stage. An alternative strategy involves a single monolithic ASV system designed to handle both zero-effort imposter (non-targets) and spoofing attacks. Such spoof-aware ASV systems have the potential to provide stronger protections and more economic computations. To this end, we propose to generalize the standalone ASV (G-SASV) against spoofing attacks, where we leverage limited training data from CM to enhance a simple backend in the embedding space, without the involvement of a separate CM module during the test (authentication) phase. We propose a novel yet simple backend classifier based on deep neural networks and conduct the study via domain adaptation and multi-task integration of spoof embeddings at the training stage. Experiments are conducted on the ASVspoof 2019 logical access dataset, where we improve the performance of statistical ASV backends on the joint (bonafide and spoofed) and spoofed conditions by a maximum of 36.2% and 49.8% in terms of equal error rates, respectively.

Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech

In this paper, we study the impact of the ageing on modern deep speaker embedding based automatic speaker verification (ASV) systems. We have selected two different datasets to examine ageing on the state-of-the-art ECAPA-TDNN system. The first dataset, used for addressing short-term ageing (up to 10 years time difference between enrollment and test) under uncontrolled conditions, is VoxCeleb. The second dataset, used for addressing long-term ageing effect (up to 40 years difference) of Finnish speakers under a more controlled setup, is Longitudinal Corpus of Finnish Spoken in Helsinki (LCFSH). Our study provides new insights into the impact of speaker ageing on modern ASV systems. Specifically, we establish a quantitative measure between ageing and ASV scores. Further, our research indicates that ageing affects female English speakers to a greater degree than male English speakers, while in the case of Finnish, it has a greater impact on male speakers than female speakers.

Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings

The adoption of advanced deep learning architectures in stuttering detection (SD) tasks is challenging due to the limited size of the available datasets. To this end, this work introduces the application of speech embeddings extracted from pre-trained deep learning models trained on large audio datasets for different tasks. In particular, we explore audio representations obtained using emphasized channel attention, propagation, and aggregation time delay neural network (ECAPA-TDNN) and Wav2Vec2.0 models trained on VoxCeleb and LibriSpeech datasets respectively. After extracting the embeddings, we benchmark with several traditional classifiers, such as the K-nearest neighbour (KNN), Gaussian naive Bayes, and neural network, for the SD tasks. In comparison to the standard SD systems trained only on the limited SEP-28k dataset, we obtain a relative improvement of 12.08%, 28.71%, 37.9% in terms of unweighted average recall (UAR) over the baselines. Finally, we have shown that combining two embeddings and concatenating multiple layers of Wav2Vec2.0 can further improve the UAR by up to 2.60% and 6.32% respectively.

Towards single integrated spoofing-aware speaker verification embeddings

This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well as target speakers' spoofed inputs should be addressed. Second, competitive performance should be demonstrated compared to the fusion of automatic speaker verification (ASV) and countermeasure (CM) embeddings, which outperformed single embedding solutions by a large margin in the SASV2022 challenge. We analyze that the inferior performance of single SASV embeddings comes from insufficient amount of training data and distinct nature of ASV and CM tasks. To this end, we propose a novel framework that includes multi-stage training and a combination of loss functions. Copy synthesis, combined with several vocoders, is also exploited to address the lack of spoofed data. Experimental results show dramatic improvements, achieving a SASV-EER of 1.06% on the evaluation protocol of the SASV2022 challenge.

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning

Shortcut learning, or `Clever Hans effect` refers to situations where a learning agent (e.g., deep neural networks) learns spurious correlations present in data, resulting in biased models. We focus on finding shortcuts in deep learning based spoofing countermeasures (CMs) that predict whether a given utterance is spoofed or not. While prior work has addressed specific data artifacts, such as silence, no general normative framework has been explored for analyzing shortcut learning in CMs. In this study, we propose a generic approach to identifying shortcuts by introducing systematic interventions on the training and test sides, including the boundary cases of `near-perfect` and `worse than coin flip` (label flip). By using three different models, ranging from classic to state-of-the-art, we demonstrate the presence of shortcut learning in five simulated conditions. We analyze the results using a regression model to understand how biases affect the class-conditional score statistics.

Speaker-Aware Anti-Spoofing

We address speaker-aware anti-spoofing, where prior knowledge of the target speaker is incorporated into a voice spoofing countermeasure (CM). In contrast to the frequently used speaker-independent solutions, we train the CM in a speaker-conditioned way. As a proof of concept, we consider speaker-aware extension to the state-of-the-art AASIST (audio anti-spoofing using integrated spectro-temporal graph attention networks) model. To this end, we consider two alternative strategies to incorporate target speaker information at the frame and utterance levels, respectively. The experimental results on a custom protocol based on ASVspoof 2019 dataset indicates the efficiency of the speaker information via enrollment: we obtain maximum relative improvements of 25.1% and 11.6% in equal error rate (EER) and minimum tandem detection cost function (t-DCF) over a speaker-independent baseline, respectively.

Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification

Deep speaker models yield low error rates in speaker verification. Nonetheless, the high performance tends to be exchanged for model size and computation time, making these models challenging to run under limited conditions. We focus on small-footprint deep speaker embedding extraction, leveraging knowledge distillation. While prior work on this topic has addressed speaker embedding extraction at the utterance level, we propose to combine embeddings from various levels of the x-vector model (teacher network) to train small-footprint student networks. Results indicate the usefulness of frame-level information, with the student models being 85%-91% smaller than their teacher, depending on the size of the teacher embeddings. Concatenation of teacher embeddings results in student networks that reach comparable performance along with the teacher while utilizing a 75% relative size reduction from the teacher. The findings and analogies are furthered to other x-vector variants.

Advancing Stuttering Detection via Data Augmentation, Class-Balanced Loss and Multi-Contextual Deep Learning

Stuttering is a neuro-developmental speech impairment characterized by uncontrolled utterances (interjections) and core behaviors (blocks, repetitions, and prolongations), and is caused by the failure of speech sensorimotors. Due to its complex nature, stuttering detection (SD) is a difficult task. If detected at an early stage, it could facilitate speech therapists to observe and rectify the speech patterns of persons who stutter (PWS). The stuttered speech of PWS is usually available in limited amounts and is highly imbalanced. To this end, we address the class imbalance problem in the SD domain via a multibranching (MB) scheme and by weighting the contribution of classes in the overall loss function, resulting in a huge improvement in stuttering classes on the SEP-28k dataset over the baseline (StutterNet). To tackle data scarcity, we investigate the effectiveness of data augmentation on top of a multi-branched training scheme. The augmented training outperforms the MB StutterNet (clean) by a relative margin of 4.18% in macro F1-score (F1). In addition, we propose a multi-contextual (MC) StutterNet, which exploits different contexts of the stuttered speech, resulting in an overall improvement of 4.48% in F 1 over the single context based MB StutterNet. Finally, we have shown that applying data augmentation in the cross-corpora scenario can improve the overall SD performance by a relative margin of 13.23% in F1 over the clean training.

Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization

This work addresses the cross-corpora generalization issue for the low-resourced spoken language identification (LID) problem. We have conducted the experiments in the context of Indian LID and identified strikingly poor cross-corpora generalization due to corpora-dependent non-lingual biases. Our contribution to this work is twofold. First, we propose domain diversification, which diversifies the limited training data using different audio data augmentation methods. We then propose the concept of maximally diversity-aware cascaded augmentations and optimize the augmentation fold-factor for effective diversification of the training data. Second, we introduce the idea of domain generalization considering the augmentation methods as pseudo-domains. Towards this, we investigate both domain-invariant and domain-aware approaches. Our LID system is based on the state-of-the-art emphasized channel attention, propagation, and aggregation based time delay neural network (ECAPA-TDNN) architecture. We have conducted extensive experiments with three widely used corpora for Indian LID research. In addition, we conduct a final blind evaluation of our proposed methods on the Indian subset of VoxLingua107 corpus collected in the wild. Our experiments demonstrate that the proposed domain diversification is more promising over commonly used simple augmentation methods. The study also reveals that domain generalization is a more effective solution than domain diversification. We also notice that domain-aware learning performs better for same-corpora LID, whereas domain-invariant learning is more suitable for cross-corpora generalization. Compared to basic ECAPA-TDNN, its proposed domain-invariant extensions improve the cross-corpora EER up to 5.23%. In contrast, the proposed domain-aware extensions also improve performance for same-corpora test scenarios.