Electrical Engineering And Systems Science

We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR. The model consists of a big size common LM and small size adapters. The model can perform multi-domain adaptation with only the small size adapters and its related layers. The proposed model can reuse the full fine-tuned LM which is fine-tuned using all layers of an original model. The proposed LM can be expanded to new domains by adding about 2% of parameters for a first domain and 13% parameters for after second domain. The proposed model is also effective in reducing the model maintenance cost because it is possible to omit the costly and time-consuming common LM pre-training process. Using proposed adapter based approach, we observed that a general LM with adapter can outperform a dedicated music domain LM in terms of word error rate (WER).

We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.

Categorical speech emotion recognition is typically performed as a sequence-to-label problem, i.e., to determine the discrete emotion label of the input utterance as a whole. One of the main challenges in practice is that most of the existing emotion corpora do not give ground truth labels for each segment; instead, we only have labels for whole utterances. To extract segment-level emotional information from such weakly labeled emotion corpora, we propose using multiple instance learning (MIL) to learn segment embeddings in a weakly supervised manner. Also, for a sufficiently long utterance, not all of the segments contain relevant emotional information. In this regard, three attention-based neural network models are then applied to the learned segment embeddings to attend the most salient part of a speech utterance. Experiments on the CASIA corpus and the IEMOCAP database show better or highly competitive results than other state-of-the-art approaches.

Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an individual's voice commands to perform diverse, and even sensitive tasks. Adversarial attack is a recently revived domain which is shown to be effective in breaking deep neural network-based classifiers, specifically, by forcing them to change their posterior distribution by only perturbing the input samples by a very small amount. Although, significant progress in this realm has been made in the computer vision domain, advances within speaker recognition is still limited. The present expository paper considers several state-of-the-art adversarial attacks to a deep speaker recognition system, employing strong defense methods as countermeasures, and reporting on several ablation studies to obtain a comprehensive understanding of the problem. The experiments show that the speaker recognition systems are vulnerable to adversarial attacks, and the strongest attacks can reduce the accuracy of the system from 94% to even 0%. The study also compares the performances of the employed defense methods in detail, and finds adversarial training based on Projected Gradient Descent (PGD) to be the best defense method in our setting. We hope that the experiments presented in this paper provide baselines that can be useful for the research community interested in further studying adversarial robustness of speaker recognition systems.

Automatic speaker verification (ASV) is one of the core technologies in biometric identification. With the ubiquitous usage of ASV systems in safety-critical applications, more and more malicious attackers attempt to launch adversarial attacks at ASV systems. In the midst of the arms race between attack and defense in ASV, how to effectively improve the robustness of ASV against adversarial attacks remains an open question. We note that the self-supervised learning models possess the ability to mitigate superficial perturbations in the input after pretraining. Hence, with the goal of effective defense in ASV against adversarial attacks, we propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks in scenarios where attackers may either be aware or unaware of the self-supervised learning models.

In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and non-targeted adversarial attacks. We firstly show that, the ResNet-56 model trained on the 2D representation of the discrete wavelet transform appended with the tonnetz chromagram outperforms other models in terms of recognition accuracy. Then we demonstrate the positive impact of adversarially training on this model as well as other deep architectures against six types of attack algorithms (white and black-box) with the cost of the reduced recognition accuracy and limited adversarial perturbation. We run our experiments on two benchmarking environmental sound datasets and show that without any imposed limitations on the budget allocations for the adversary, the fooling rate of the adversarially trained models can exceed 90\%. In other words, adversarial attacks exist in any scales, but they might require higher adversarial perturbations compared to non-adversarially trained models.

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and content, lacking controllability on other prosody-related factors. State-of-the-art speech representation learning methods for more speech factors are using primary disentangle algorithms such as random resampling and ad-hoc bottleneck layer size adjustment, which however is hard to ensure robust speech representation disentanglement. To increase the robustness of highly controllable style transfer on multiple factors in VC, we propose a disentangled speech representation learning framework based on adversarial learning. Four speech representations characterizing content, timbre, rhythm and pitch are extracted, and further disentangled by an adversarial network inspired by BERT. The adversarial network is used to minimize the correlations between the speech representations, by randomly masking and predicting one of the representations from the others. A word prediction network is also adopted to learn a more informative content representation. Experimental results show that the proposed speech representation learning framework significantly improves the robustness of VC on multiple factors by increasing conversion rate from 48.2% to 57.1% and ABX preference exceeding by 31.2% compared with state-of-the-art method.

Automatic detection of Alzheimer's dementia by speech processing is enhanced when features of both the acoustic waveform and the content are extracted. Audio and text transcription have been widely used in health-related tasks, as spectral and prosodic speech features, as well as semantic and linguistic content, convey information about various diseases. Hence, this paper describes the joint work of the GTM-UVIGO research group and acceXible startup to the ADDReSS challenge at INTERSPEECH 2020. The submitted systems aim to detect patterns of Alzheimer's disease from both the patient's voice and message transcription. Six different systems have been built and compared: four of them are speech-based and the other two systems are text-based. The x-vector, i-vector, and statistical speech-based functionals features are evaluated. As a lower speaking fluency is a common pattern in patients with Alzheimer's disease, rhythmic features are also proposed. For transcription analysis, two systems are proposed: one uses GloVe word embedding features and the other uses several features extracted by language modelling. Several intra-modality and inter-modality score fusion strategies are investigated. The performance of single modality and multimodal systems are presented. The achieved results are promising, outperforming the results achieved by the ADDReSS's baseline systems.

In this paper, we propose a sub-utterance unit selection framework to remove acoustic segments in audio recordings that carry little information for acoustic scene classification (ASC). Our approach is built upon a universal set of acoustic segment units covering the overall acoustic scene space. First, those units are modeled with acoustic segment models (ASMs) used to tokenize acoustic scene utterances into sequences of acoustic segment units. Next, paralleling the idea of stop words in information retrieval, stop ASMs are automatically detected. Finally, acoustic segments associated with the stop ASMs are blocked, because of their low indexing power in retrieval of most acoustic scenes. In contrast to building scene models with whole utterances, the ASM-removed sub-utterances, i.e., acoustic utterances without stop acoustic segments, are then used as inputs to the AlexNet-L back-end for final classification. On the DCASE 2018 dataset, scene classification accuracy increases from 68%, with whole utterances, to 72.1%, with segment selection. This represents a competitive accuracy without any data augmentation, and/or ensemble strategy. Moreover, our approach compares favourably to AlexNet-L with attention.

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas a remedy to this problem. Previously, we introduced a sys-tem, calledunmixing,fixed-beamformerandextraction(UFE),that was shown to be effective in addressing the speech over-lap problem in conversation transcription. With UFE, an inputmixed signal is processed by fixed beamformers, followed by aneural network post filtering. Although promising results wereobtained, the system contains multiple individually developedmodules, leading potentially sub-optimum performance. In thiswork, we introduce an end-to-end modeling version of UFE. Toenable gradient propagation all the way, an attentional selectionmodule is proposed, where an attentional weight is learnt foreach beamformer and spatial feature sampled over space. Ex-perimental results show that the proposed system achieves com-parable performance in an offline evaluation with the originalseparate processing-based pipeline, while producing remark-able improvements in an online evaluation.