Paralinguistic properties of speech are essential in analyzing and choosing optimal treatment options for patients with speech disorders. However, automatic modeling of these characteristics is difficult due to the lack of labeled speech datasets describing paralinguistic properties, especially at the frame-level. In this paper, we propose a weakly supervised training method which exploits the known acoustic properties of phonemes by training an ASR model with an interpretable frame-level phonological feature bottleneck layer. Subsequently, we assess the viability of these phonological features in speech pathology analysis by developing corresponding models for intelligibility prediction and speech pathology classification. Models using our proposed phonological features perform similar to other state-of-the-art acoustic features on both tasks with a classification accuracy of 75% and a 8.43 RMSE on speech intelligibility prediction. In contrast to others, our phonological features are text-independent and highly interpretable, providing potentially useful insights for speech therapists.

In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings. Most speaker verification models are based on either the 1D- or 2D-convolutional operation, often manifested as Time Delay Neural Networks or ResNets, respectively. Hybrid models are relatively unexplored without an intuitive explanation what constitutes best practices in regard to its architectural choices. We motivate the proposed ECAPA2 model in this paper with an analysis of current speaker verification architectures. In addition, we propose a training strategy which makes the speaker embeddings more robust against overlapping speech and short utterance lengths. The presented ECAPA2 architecture and training strategy attains state-of-the-art performance on the VoxCeleb1 test sets with significantly less parameters than current models. Finally, we make a pre-trained model publicly available to promote research on downstream tasks.

For separating sources captured by ad hoc distributed microphones a key first step is assigning the microphones to the appropriate source-dominated clusters. The features used for such (blind) clustering are based on a fixed length embedding of the audio signals in a high-dimensional latent space. In previous work, the embedding was hand-engineered from the Mel frequency cepstral coefficients and their modulation-spectra. This paper argues that embedding frameworks designed explicitly for the purpose of reliably discriminating between speakers would produce more appropriate features. We propose features generated by the state-of-the-art ECAPA-TDNN speaker verification model for the clustering. We benchmark these features in terms of the subsequent signal enhancement as well as on the quality of the clustering where, further, we introduce 3 intuitive metrics for the latter. Results indicate that in contrast to the hand-engineered features, the ECAPA-TDNN-based features lead to more logical clusters and better performance in the subsequent enhancement stages - thus validating our hypothesis.

This paper is concerned with the task of speaker verification on audio with multiple overlapping speakers. Most speaker verification systems are designed with the assumption of a single speaker being present in a given audio segment. However, in a real-world setting this assumption does not always hold. In this paper, we demonstrate that current speaker verification systems are not robust against audio with noticeable speaker overlap. To alleviate this issue, we propose margin-mixup, a simple training strategy that can easily be adopted by existing speaker verification pipelines to make the resulting speaker embeddings robust against multi-speaker audio. In contrast to other methods, margin-mixup requires no alterations to regular speaker verification architectures, while attaining better results. On our multi-speaker test set based on VoxCeleb1, the proposed margin-mixup strategy improves the EER on average with 44.4% relative to our state-of-the-art speaker verification baseline systems.

In this paper, we analyze the behavior of speaker embeddings of patients during oral cancer treatment. First, we found that pre- and post-treatment speaker embeddings differ significantly, notifying a substantial change in voice characteristics. However, a partial recovery to pre-operative voice traits is observed after 12 months post-operation. Secondly, the same-speaker similarity at distinct treatment stages is similar to healthy speakers, indicating that the embeddings can capture characterizing features of even severely impaired speech. Finally, a speaker verification analysis signifies a stable false positive rate and variable false negative rate when combining speech samples of different treatment stages. This indicates robustness of the embeddings towards other speakers, while still capturing the changing voice characteristics during treatment. To the best of our knowledge, this is the first analysis of speaker embeddings during oral cancer treatment of patients.

This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding extractors consistently underestimate speaker similarity in within-speaker cross-lingual trials. Consequently, the typical training and scoring protocols do not put enough emphasis on the compensation of intra-speaker language variability. We propose two techniques to increase cross-lingual speaker verification robustness. First, we enhance our previously proposed Large-Margin Fine-Tuning (LM-FT) training stage with a mini-batch sampling strategy which increases the amount of intra-speaker cross-lingual samples within the mini-batch. Second, we incorporate language information in the logistic regression calibration stage. We integrate quality metrics based on soft and hard decisions of a VoxLingua107 language identification model. The proposed techniques result in a 11.7% relative improvement over the baseline model on the VoxSRC-21 test set and contributed to our third place finish in the corresponding challenge.

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting domain mismatch when decoding children's speech with systems trained on adult data. In this paper, we propose multiple enhancements to alleviate these issues. First, we propose a data augmentation technique based on the source-filter model of speech to close the domain gap between adult and children's speech. This enables us to leverage the data availability of adult speech corpora by making these samples perceptually similar to children's speech. Second, using this augmentation strategy, we apply transfer learning on a Transformer model pre-trained on adult data. This model follows the recently introduced XLS-R architecture, a wav2vec 2.0 model pre-trained on several cross-lingual adult speech corpora to learn general and robust acoustic frame-level representations. Adopting this model for the ASR task using adult data augmented with the proposed source-filter warping strategy and a limited amount of in-domain children's speech significantly outperforms previous state-of-the-art results on the PF-STAR British English Children's Speech corpus with a 4.86% WER on the official test set.

In this paper we propose and analyse a large margin fine-tuning strategy and a quality-aware score calibration in text-independent speaker verification. Large margin fine-tuning is a secondary training stage for DNN based speaker verification systems trained with margin-based loss functions. It enables the network to create more robust speaker embeddings by enabling the use of longer training utterances in combination with a more aggressive margin penalty. Score calibration is a common practice in speaker verification systems to map output scores to well-calibrated log-likelihood-ratios, which can be converted to interpretable probabilities. By including quality features in the calibration system, the decision thresholds of the evaluation metrics become quality-dependent and more consistent across varying trial conditions. Applying both enhancements on the ECAPA-TDNN architecture leads to state-of-the-art results on all publicly available VoxCeleb1 test sets and contributed to our winning submissions in the supervised verification tracks of the Vox-Celeb Speaker Recognition Challenge 2020.

Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental component of modern diarization systems. Recently, some improvements over the standard TDNN architecture used for x-vectors have been proposed. The ECAPA-TDNN model, for instance, has shown impressive performance in the speaker verification domain, thanks to a carefully designed neural model. In this work, we extend, for the first time, the use of the ECAPA-TDNN model to speaker diarization. Moreover, we improved its robustness with a powerful augmentation scheme that concatenates several contaminated versions of the same signal within the same training batch. The ECAPA-TDNN model turned out to provide robust speaker embeddings under both close-talking and distant-talking conditions. Our results on the popular AMI meeting corpus show that our system significantly outperforms recently proposed approaches.

This paper describes the IDLab submission for the text-independent task of the Short-duration Speaker Verification Challenge 2021 (SdSVC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual trials, along with the constraint of limited availability of in-domain DeepMine Farsi training data. Currently, both Time Delay Neural Networks (TDNNs) and ResNets achieve state-of-the-art results in speaker verification. These architectures are structurally very different and the construction of hybrid networks looks a promising way forward. We introduce a 2D convolutional stem in a strong ECAPA-TDNN baseline to transfer some of the strong characteristics of a ResNet based model to this hybrid CNN-TDNN architecture. Similarly, we incorporate absolute frequency positional encodings in an SE-ResNet34 architecture. These learnable feature map biases along the frequency axis offer this architecture a straightforward way to exploit frequency positional information. We also propose a frequency-wise variant of Squeeze-Excitation (SE) which better preserves frequency-specific information when rescaling the feature maps. Both modified architectures significantly outperform their corresponding baseline on the SdSVC-21 evaluation data and the original VoxCeleb1 test set. A four system fusion containing the two improved architectures achieved a third place in the final SdSVC-21 Task 2 ranking.

Current speaker verification techniques rely on a neural network to extract speaker representations. The successful x-vector architecture is a Time Delay Neural Network (TDNN) that applies statistics pooling to project variable-length utterances into fixed-length speaker characterizing embeddings. In this paper, we propose multiple enhancements to this architecture based on recent trends in the related fields of face verification and computer vision. Firstly, the initial frame layers can be restructured into 1-dimensional Res2Net modules with impactful skip connections. Similarly to SE-ResNet, we introduce Squeeze-and-Excitation blocks in these modules to explicitly model channel interdependencies. The SE block expands the temporal context of the frame layer by rescaling the channels according to global properties of the recording. Secondly, neural networks are known to learn hierarchical features, with each layer operating on a different level of complexity. To leverage this complementary information, we aggregate and propagate features of different hierarchical levels. Finally, we improve the statistics pooling module with channel-dependent frame attention. This enables the network to focus on different subsets of frames during each of the channel's statistics estimation. The proposed ECAPA-TDNN architecture significantly outperforms state-of-the-art TDNN based systems on the VoxCeleb test sets and the 2019 VoxCeleb Speaker Recognition Challenge.

In this paper we describe the top-scoring IDLab submission for the text-independent task of the Short-duration Speaker Verification (SdSV) Challenge 2020. The main difficulty of the challenge exists in the large degree of varying phonetic overlap between the potentially cross-lingual trials, along with the limited availability of in-domain DeepMine Farsi training data. We introduce domain-balanced hard prototype mining to fine-tune the state-of-the-art ECAPA-TDNN x-vector based speaker embedding extractor. The sample mining technique efficiently exploits speaker distances between the speaker prototypes of the popular AAM-softmax loss function to construct challenging training batches that are balanced on the domain-level. To enhance the scoring of cross-lingual trials, we propose a language-dependent s-norm score normalization. The imposter cohort only contains data from the Farsi target-domain which simulates the enrollment data always being Farsi. In case a Gaussian-Backend language model detects the test speaker embedding to contain English, a cross-language compensation offset determined on the AAM-softmax speaker prototypes is subtracted from the maximum expected imposter mean score. A fusion of five systems with minor topological tweaks resulted in a final MinDCF and EER of 0.065 and 1.45% respectively on the SdSVC evaluation set.