Different studies have shown the importance of visual cues throughout the speech perception process. In fact, the development of audiovisual approaches has led to advances in the field of speech technologies. However, although noticeable results have recently been achieved, visual speech recognition remains an open research problem. It is a task in which, by dispensing with the auditory sense, challenges such as visual ambiguities and the complexity of modeling silence must be faced. Nonetheless, some of these challenges can be alleviated when the problem is approached from a speaker-dependent perspective. Thus, this paper studies, using the Spanish LIP-RTVE database, how the estimation of specialized end-to-end systems for a specific person could affect the quality of speech recognition. First, different adaptation strategies based on the fine-tuning technique were proposed. Then, a pre-trained CTC/Attention architecture was used as a baseline throughout our experiments. Our findings showed that a two-step fine-tuning process, where the VSR system is first adapted to the task domain, provided significant improvements when the speaker adaptation was addressed. Furthermore, results comparable to the current state of the art were reached even when only a limited amount of data was available.
The widespread smart devices raise people's concerns of being eavesdropped on. To enhance voice privacy, recent studies exploit the nonlinearity in microphone to jam audio recorders with inaudible ultrasound. However, existing solutions solely rely on energetic masking. Their simple-form noise leads to several problems, such as high energy requirements and being easily removed by speech enhancement techniques. Besides, most of these solutions do not support authorized recording, which restricts their usage scenarios. In this paper, we design an efficient yet robust system that can jam microphones while preserving authorized recording. Specifically, we propose a novel phoneme-based noise with the idea of informational masking, which can distract both machines and humans and is resistant to denoising techniques. Besides, we optimize the noise transmission strategy for broader coverage and implement a hardware prototype of our system. Experimental results show that our system can reduce the recognition accuracy of recordings to below 50\% under all tested speech recognition systems, which is much better than existing solutions.
The Streaming Unmixing and Recognition Transducer (SURT) has recently become a popular framework for continuous, streaming, multi-talker speech recognition (ASR). With advances in architecture, objectives, and mixture simulation methods, it was demonstrated that SURT can be an efficient streaming method for speaker-agnostic transcription of real meetings. In this work, we push this framework further by proposing methods to perform speaker-attributed transcription with SURT, for both short mixtures and long recordings. We achieve this by adding an auxiliary speaker branch to SURT, and synchronizing its label prediction with ASR token prediction through HAT-style blank factorization. In order to ensure consistency in relative speaker labels across different utterance groups in a recording, we propose "speaker prefixing" -- appending each chunk with high-confidence frames of speakers identified in previous chunks, to establish the relative order. We perform extensive ablation experiments on synthetic LibriSpeech mixtures to validate our design choices, and demonstrate the efficacy of our final model on the AMI corpus.
Alzheimer's disease is a common cognitive disorder in the elderly. Early and accurate diagnosis of Alzheimer's disease (AD) has a major impact on the progress of research on dementia. At present, researchers have used machine learning methods to detect Alzheimer's disease from the speech of participants. However, the recognition accuracy of current methods is unsatisfactory, and most of them focus on using low-dimensional handcrafted features to extract relevant information from audios. This paper proposes an Alzheimer's disease detection system based on the pre-trained framework Wav2vec 2.0 (Wav2vec2). In addition, by replacing the loss function with the Soft-Weighted CrossEntropy loss function, we achieved 85.45\% recognition accuracy on the same test dataset.
End-to-end automatic speech recognition (ASR) models have seen revolutionary quality gains with the recent development of large-scale universal speech models (USM). However, deploying these massive USMs is extremely expensive due to the enormous memory usage and computational cost. Therefore, model compression is an important research topic to fit USM-based ASR under budget in real-world scenarios. In this study, we propose a USM fine-tuning approach for ASR, with a low-bit quantization and N:M structured sparsity aware paradigm on the model weights, reducing the model complexity from parameter precision and matrix topology perspectives. We conducted extensive experiments with a 2-billion parameter USM on a large-scale voice search dataset to evaluate our proposed method. A series of ablation studies validate the effectiveness of up to int4 quantization and 2:4 sparsity. However, a single compression technique fails to recover the performance well under extreme setups including int2 quantization and 1:4 sparsity. By contrast, our proposed method can compress the model to have 9.4% of the size, at the cost of only 7.3% relative word error rate (WER) regressions. We also provided in-depth analyses on the results and discussions on the limitations and potential solutions, which would be valuable for future studies.
Machine learning models for speech emotion recognition (SER) can be trained for different tasks and are usually evaluated on the basis of a few available datasets per task. Tasks could include arousal, valence, dominance, emotional categories, or tone of voice. Those models are mainly evaluated in terms of correlation or recall, and always show some errors in their predictions. The errors manifest themselves in model behaviour, which can be very different along different dimensions even if the same recall or correlation is achieved by the model. This paper investigates behavior of speech emotion recognition models with a testing framework which requires models to fulfill conditions in terms of correctness, fairness, and robustness.
Speech-to-Text Translation (S2TT) has typically been addressed with cascade systems, where speech recognition systems generate a transcription that is subsequently passed to a translation model. While there has been a growing interest in developing direct speech translation systems to avoid propagating errors and losing non-verbal content, prior work in direct S2TT has struggled to conclusively establish the advantages of integrating the acoustic signal directly into the translation process. This work proposes using contrastive evaluation to quantitatively measure the ability of direct S2TT systems to disambiguate utterances where prosody plays a crucial role. Specifically, we evaluated Korean-English translation systems on a test set containing wh-phrases, for which prosodic features are necessary to produce translations with the correct intent, whether it's a statement, a yes/no question, a wh-question, and more. Our results clearly demonstrate the value of direct translation systems over cascade translation models, with a notable 12.9% improvement in overall accuracy in ambiguous cases, along with up to a 15.6% increase in F1 scores for one of the major intent categories. To the best of our knowledge, this work stands as the first to provide quantitative evidence that direct S2TT models can effectively leverage prosody. The code for our evaluation is openly accessible and freely available for review and utilisation.
Neural networks have become popular due to their versatility and state-of-the-art results in many applications, such as image classification, natural language processing, speech recognition, forecasting, etc. These applications are also used in resource-constrained environments such as embedded devices. In this work, the susceptibility of neural network implementations to reverse engineering is explored on the NVIDIA Jetson Nano microcomputer via side-channel analysis. To this end, an architecture extraction attack is presented. In the attack, 15 popular convolutional neural network architectures (EfficientNets, MobileNets, NasNet, etc.) are implemented on the GPU of Jetson Nano and the electromagnetic radiation of the GPU is analyzed during the inference operation of the neural networks. The results of the analysis show that neural network architectures are easily distinguishable using deep learning-based side-channel analysis.
Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are selected from a large pool of phrases following a sampling strategy. In this work we firstly analyse different sampling strategies to provide insights into the training of CB for ASR with correlation plots between the bias embeddings among various training stages. Secondly, we introduce a neighbourhood attention (NA) that localizes self attention (SA) to the nearest neighbouring frames to further refine the CB output. The results show that this proposed approach provides on average a 25.84% relative WER improvement on LibriSpeech sets and rare-word evaluation compared to the baseline.
Speaker adaptation systems face privacy concerns, for such systems are trained on private datasets and often overfitting. This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech recognition (ASR) systems. We focus on the speaker information of a transformer-based ASR and propose GhostVec, a simple and efficient attack method to extract the speaker information from an encoder-decoder-based ASR system without any external speaker verification system or natural human voice as a reference. To make our results quantitative, we pre-process GhostVec using singular value decomposition (SVD) and synthesize it into waveform. Experiment results show that the synthesized audio of GhostVec reaches 10.83\% EER and 0.47 minDCF with target speakers, which suggests the effectiveness of the proposed method. We hope the preliminary discovery in this study to catalyze future speech recognition research on privacy-preserving topics.