Multimodal Emotion Recognition from Raw Audio with Sinc-convolution

Speech Emotion Recognition (SER) is still a complex task for computers with average recall rates usually about 70% on the most realistic datasets. Most SER systems use hand-crafted features extracted from audio signal such as energy, zero crossing rate, spectral information, prosodic, mel frequency cepstral coefficient (MFCC), and so on. More recently, using raw waveform for training neural network is becoming an emerging trend. This approach is advantageous as it eliminates the feature extraction pipeline. Learning from time-domain signal has shown good results for tasks such as speech recognition, speaker verification etc. In this paper, we utilize Sinc-convolution layer, which is an efficient architecture for preprocessing raw speech waveform for emotion recognition, to extract acoustic features from raw audio signals followed by a long short-term memory (LSTM). We also incorporate linguistic features and append a dialogical emotion decoding (DED) strategy. Our approach achieves a weighted accuracy of 85.1\% in four class emotion on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) dataset.

Soft-Weighted CrossEntropy Loss for Continous Alzheimer's Disease Detection

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.

Attention-Based CNN-BiLSTM for Sleep State Classification of Spatiotemporal Wide-Field Calcium Imaging Data

Background: Wide-field calcium imaging (WFCI) with genetically encoded calcium indicators allows for spatiotemporal recordings of neuronal activity in mice. When applied to the study of sleep, WFCI data are manually scored into the sleep states of wakefulness, non-REM (NREM) and REM by use of adjunct EEG and EMG recordings. However, this process is time-consuming, invasive and often suffers from low inter- and intra-rater reliability. Therefore, an automated sleep state classification method that operates on spatiotemporal WFCI data is desired. New Method: A hybrid network architecture consisting of a convolutional neural network (CNN) to extract spatial features of image frames and a bidirectional long short-term memory network (BiLSTM) with attention mechanism to identify temporal dependencies among different time points was proposed to classify WFCI data into states of wakefulness, NREM and REM sleep. Results: Sleep states were classified with an accuracy of 84% and Cohen's kappa of 0.64. Gradient-weighted class activation maps revealed that the frontal region of the cortex carries more importance when classifying WFCI data into NREM sleep while posterior area contributes most to the identification of wakefulness. The attention scores indicated that the proposed network focuses on short- and long-range temporal dependency in a state-specific manner. Comparison with Existing Method: On a 3-hour WFCI recording, the CNN-BiLSTM achieved a kappa of 0.67, comparable to a kappa of 0.65 corresponding to the human EEG/EMG-based scoring. Conclusions: The CNN-BiLSTM effectively classifies sleep states from spatiotemporal WFCI data and will enable broader application of WFCI in sleep.

What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection

The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms. Existing detection models have shown remarkable success in discriminating known deepfake audio, but struggle when encountering new attack types. To address this challenge, one of the emergent effective approaches is continual learning. In this paper, we propose a continual learning approach called Radian Weight Modification (RWM) for audio deepfake detection. The fundamental concept underlying RWM involves categorizing all classes into two groups: those with compact feature distributions across tasks, such as genuine audio, and those with more spread-out distributions, like various types of fake audio. These distinctions are quantified by means of the in-class cosine distance, which subsequently serves as the basis for RWM to introduce a trainable gradient modification direction for distinct data types. Experimental evaluations against mainstream continual learning methods reveal the superiority of RWM in terms of knowledge acquisition and mitigating forgetting in audio deepfake detection. Furthermore, RWM's applicability extends beyond audio deepfake detection, demonstrating its potential significance in diverse machine learning domains such as image recognition.

Multimodal Representation Learning by Alternating Unimodal Adaptation

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant than others during multimodal learning, resulting in suboptimal performance. To address this challenge, we propose MLA (Multimodal Learning with Alternating Unimodal Adaptation). MLA reframes the conventional joint multimodal learning process by transforming it into an alternating unimodal learning process, thereby minimizing interference between modalities. Simultaneously, it captures cross-modal interactions through a shared head, which undergoes continuous optimization across different modalities. This optimization process is controlled by a gradient modification mechanism to prevent the shared head from losing previously acquired information. During the inference phase, MLA utilizes a test-time uncertainty-based model fusion mechanism to integrate multimodal information. Extensive experiments are conducted on five diverse datasets, encompassing scenarios with complete modalities and scenarios with missing modalities. These experiments demonstrate the superiority of MLA over competing prior approaches.

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing well-designed, easy-to-use, and performant PyTorch components. Its contributors routinely engage with users to understand their needs and fulfill them by developing impactful features. Here, we survey TorchAudio's development principles and contents and highlight key features we include in its latest version (2.1): self-supervised learning pre-trained pipelines and training recipes, high-performance CTC decoders, speech recognition models and training recipes, advanced media I/O capabilities, and tools for performing forced alignment, multi-channel speech enhancement, and reference-less speech assessment. For a selection of these features, through empirical studies, we demonstrate their efficacy and show that they achieve competitive or state-of-the-art performance.

Deep learning-based image super-resolution of a novel end-expandable optical fiber probe for application in esophageal cancer diagnostics

Significance: Endoscopic screening for esophageal cancer may enable early cancer diagnosis and treatment. While optical microendoscopic technology has shown promise in improving specificity, the limited field of view (<1 mm) significantly reduces the ability to survey large areas efficiently in esophageal cancer screening. Aim: To improve the efficiency of endoscopic screening, we proposed a novel end-expandable endoscopic optical fiber probe for larger field of visualization and employed a deep learning-based image super-resolution (DL-SR) method to overcome the issue of limited sampling capability. Approach: To demonstrate feasibility of the end-expandable optical fiber probe, DL-SR was applied on simulated low-resolution (LR) microendoscopic images to generate super-resolved (SR) ones. Varying the degradation model of image data acquisition, we identified the optimal parameters for optical fiber probe prototyping. The proposed screening method was validated with a human pathology reading study. Results: For various degradation parameters considered, the DL-SR method demonstrated different levels of improvement of traditional measures of image quality. The endoscopist interpretations of the SR images were comparable to those performed on the high-resolution ones. Conclusions: This work suggests avenues for development of DL-SR-enabled end-expandable optical fiber probes to improve high-yield esophageal cancer screening.

Exploring Speech Enhancement for Low-resource Speech Synthesis

High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech Recognition (ASR) corpus mitigates the issue by augmenting the training data, while how the nonlinear speech distortion brought by speech enhancement models affects TTS training still needs to be investigated. In this paper, we train a TF-GridNet speech enhancement model and apply it to low-resource datasets that were collected for the ASR task, then train a discrete unit based TTS model on the enhanced speech. We use Arabic datasets as an example and show that the proposed pipeline significantly improves the low-resource TTS system compared with other baseline methods in terms of ASR WER metric. We also run empirical analysis on the correlation between speech enhancement and TTS performances.

Audio Deepfake Detection: A Survey

Audio deepfake detection is an emerging active topic. A growing number of literatures have aimed to study deepfake detection algorithms and achieved effective performance, the problem of which is far from being solved. Although there are some review literatures, there has been no comprehensive survey that provides researchers with a systematic overview of these developments with a unified evaluation. Accordingly, in this survey paper, we first highlight the key differences across various types of deepfake audio, then outline and analyse competitions, datasets, features, classifications, and evaluation of state-of-the-art approaches. For each aspect, the basic techniques, advanced developments and major challenges are discussed. In addition, we perform a unified comparison of representative features and classifiers on ASVspoof 2021, ADD 2023 and In-the-Wild datasets for audio deepfake detection, respectively. The survey shows that future research should address the lack of large scale datasets in the wild, poor generalization of existing detection methods to unknown fake attacks, as well as interpretability of detection results.

Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection

Current fake audio detection algorithms have achieved promising performances on most datasets. However, their performance may be significantly degraded when dealing with audio of a different dataset. The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets. To overcome this limitation, we propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting, called Regularized Adaptive Weight Modification (RAWM). When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. The adaptive modification direction ensures the network can effectively detect fake audio on the new dataset while preserving its knowledge of old model, thus mitigating catastrophic forgetting. In addition, genuine audio collected from quite different acoustic conditions may skew their feature distribution, so we introduce a regularization constraint to force the network to remember the old distribution in this regard. Our method can easily be generalized to related fields, like speech emotion recognition. We also evaluate our approach across multiple datasets and obtain a significant performance improvement on cross-dataset experiments.