ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis

Prosody contains rich information beyond the literal meaning of words, which is crucial for the intelligibility of speech. Current models still fall short in phrasing and intonation; they not only miss or misplace breaks when synthesizing long sentences with complex structures but also produce unnatural intonation. We propose ProsodyFM, a prosody-aware text-to-speech synthesis (TTS) model with a flow-matching (FM) backbone that aims to enhance the phrasing and intonation aspects of prosody. ProsodyFM introduces two key components: a Phrase Break Encoder to capture initial phrase break locations, followed by a Duration Predictor for the flexible adjustment of break durations; and a Terminal Intonation Encoder which integrates a set of intonation shape tokens combined with a novel Pitch Processor for more robust modeling of human-perceived intonation change. ProsodyFM is trained with no explicit prosodic labels and yet can uncover a broad spectrum of break durations and intonation patterns. Experimental results demonstrate that ProsodyFM can effectively improve the phrasing and intonation aspects of prosody, thereby enhancing the overall intelligibility compared to four state-of-the-art (SOTA) models. Out-of-distribution experiments show that this prosody improvement can further bring ProsodyFM superior generalizability for unseen complex sentences and speakers. Our case study intuitively illustrates the powerful and fine-grained controllability of ProsodyFM over phrasing and intonation.

Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition

With the increasing implementation of machine learning models on edge or Internet-of-Things (IoT) devices, deploying advanced models on resource-constrained IoT devices remains challenging. Transformer models, a currently dominant neural architecture, have achieved great success in broad domains but their complexity hinders its deployment on IoT devices with limited computation capability and storage size. Although many model compression approaches have been explored, they often suffer from notorious performance degradation. To address this issue, we introduce a new method, namely Transformer Re-parameterization, to boost the performance of lightweight Transformer models. It consists of two processes: the High-Rank Factorization (HRF) process in the training stage and the deHigh-Rank Factorization (deHRF) process in the inference stage. In the former process, we insert an additional linear layer before the Feed-Forward Network (FFN) of the lightweight Transformer. It is supposed that the inserted HRF layers can enhance the model learning capability. In the later process, the auxiliary HRF layer will be merged together with the following FFN layer into one linear layer and thus recover the original structure of the lightweight model. To examine the effectiveness of the proposed method, we evaluate it on three widely used Transformer variants, i.e., ConvTransformer, Conformer, and SpeechFormer networks, in the application of speech emotion recognition on the IEMOCAP, M3ED and DAIC-WOZ datasets. Experimental results show that our proposed method consistently improves the performance of lightweight Transformers, even making them comparable to large models. The proposed re-parameterization approach enables advanced Transformer models to be deployed on resource-constrained IoT devices.

ParaLBench: A Large-Scale Benchmark for Computational Paralinguistics over Acoustic Foundation Models

Computational paralinguistics (ComParal) aims to develop algorithms and models to automatically detect, analyze, and interpret non-verbal information from speech communication, e. g., emotion, health state, age, and gender. Despite its rapid progress, it heavily depends on sophisticatedly designed models given specific paralinguistic tasks. Thus, the heterogeneity and diversity of ComParal models largely prevent the realistic implementation of ComParal models. Recently, with the advent of acoustic foundation models because of self-supervised learning, developing more generic models that can efficiently perceive a plethora of paralinguistic information has become an active topic in speech processing. However, it lacks a unified evaluation framework for a fair and consistent performance comparison. To bridge this gap, we conduct a large-scale benchmark, namely ParaLBench, which concentrates on standardizing the evaluation process of diverse paralinguistic tasks, including critical aspects of affective computing such as emotion recognition and emotion dimensions prediction, over different acoustic foundation models. This benchmark contains ten datasets with thirteen distinct paralinguistic tasks, covering short-, medium- and long-term characteristics. Each task is carried out on 14 acoustic foundation models under a unified evaluation framework, which allows for an unbiased methodological comparison and offers a grounded reference for the ComParal community. Based on the insights gained from ParaLBench, we also point out potential research directions, i.e., the cross-corpus generalizability, to propel ComParal research in the future. The code associated with this study will be available to foster the transparency and replicability of this work for succeeding researchers.

Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling

The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL) framework, introducing a novel multi-view pseudo-labeling method that leverages both acoustic and linguistic characteristics to select the most confident data for training the classification model. Acoustically, unlabeled data are compared to labeled data using the Frechet audio distance, calculated from embeddings generated by multiple audio encoders. Linguistically, large language models are prompted to revise automatic speech recognition transcriptions and predict labels based on our proposed task-specific knowledge. High-confidence data are identified when pseudo-labels from both sources align, while mismatches are treated as low-confidence data. A bimodal classifier is then trained to iteratively label the low-confidence data until a predefined criterion is met. We evaluate our SSL framework on emotion recognition and dementia detection tasks. Experimental results demonstrate that our method achieves competitive performance compared to fully supervised learning using only 30% of the labeled data and significantly outperforms two selected baselines.

DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System

Benefiting from the strong reasoning capabilities, Large language models (LLMs) have demonstrated remarkable performance in recommender systems. Various efforts have been made to distill knowledge from LLMs to enhance collaborative models, employing techniques like contrastive learning for representation alignment. In this work, we prove that directly aligning the representations of LLMs and collaborative models is sub-optimal for enhancing downstream recommendation tasks performance, based on the information theorem. Consequently, the challenge of effectively aligning semantic representations between collaborative models and LLMs remains unresolved. Inspired by this viewpoint, we propose a novel plug-and-play alignment framework for LLMs and collaborative models. Specifically, we first disentangle the latent representations of both LLMs and collaborative models into specific and shared components via projection layers and representation regularization. Subsequently, we perform both global and local structure alignment on the shared representations to facilitate knowledge transfer. Additionally, we theoretically prove that the specific and shared representations contain more pertinent and less irrelevant information, which can enhance the effectiveness of downstream recommendation tasks. Extensive experimental results on benchmark datasets demonstrate that our method is superior to existing state-of-the-art algorithms.

ESIHGNN: Event-State Interactions Infused Heterogeneous Graph Neural Network for Conversational Emotion Recognition

Conversational Emotion Recognition (CER) aims to predict the emotion expressed by an utterance (referred to as an ``event'') during a conversation. Existing graph-based methods mainly focus on event interactions to comprehend the conversational context, while overlooking the direct influence of the speaker's emotional state on the events. In addition, real-time modeling of the conversation is crucial for real-world applications but is rarely considered. Toward this end, we propose a novel graph-based approach, namely Event-State Interactions infused Heterogeneous Graph Neural Network (ESIHGNN), which incorporates the speaker's emotional state and constructs a heterogeneous event-state interaction graph to model the conversation. Specifically, a heterogeneous directed acyclic graph neural network is employed to dynamically update and enhance the representations of events and emotional states at each turn, thereby improving conversational coherence and consistency. Furthermore, to further improve the performance of CER, we enrich the graph's edges with external knowledge. Experimental results on four publicly available CER datasets show the superiority of our approach and the effectiveness of the introduced heterogeneous event-state interaction graph.

HAFFormer: A Hierarchical Attention-Free Framework for Alzheimer's Disease Detection From Spontaneous Speech

Automatically detecting Alzheimer's Disease (AD) from spontaneous speech plays an important role in its early diagnosis. Recent approaches highly rely on the Transformer architectures due to its efficiency in modelling long-range context dependencies. However, the quadratic increase in computational complexity associated with self-attention and the length of audio poses a challenge when deploying such models on edge devices. In this context, we construct a novel framework, namely Hierarchical Attention-Free Transformer (HAFFormer), to better deal with long speech for AD detection. Specifically, we employ an attention-free module of Multi-Scale Depthwise Convolution to replace the self-attention and thus avoid the expensive computation, and a GELU-based Gated Linear Unit to replace the feedforward layer, aiming to automatically filter out the redundant information. Moreover, we design a hierarchical structure to force it to learn a variety of information grains, from the frame level to the dialogue level. By conducting extensive experiments on the ADReSS-M dataset, the introduced HAFFormer can achieve competitive results (82.6% accuracy) with other recent work, but with significant computational complexity and model size reduction compared to the standard Transformer. This shows the efficiency of HAFFormer in dealing with long audio for AD detection.

Intelligent Cardiac Auscultation for Murmur Detection via Parallel-Attentive Models with Uncertainty Estimation

Heart murmurs are a common manifestation of cardiovascular diseases and can provide crucial clues to early cardiac abnormalities. While most current research methods primarily focus on the accuracy of models, they often overlook other important aspects such as the interpretability of machine learning algorithms and the uncertainty of predictions. This paper introduces a heart murmur detection method based on a parallel-attentive model, which consists of two branches: One is based on a self-attention module and the other one is based on a convolutional network. Unlike traditional approaches, this structure is better equipped to handle long-term dependencies in sequential data, and thus effectively captures the local and global features of heart murmurs. Additionally, we acknowledge the significance of understanding the uncertainty of model predictions in the medical field for clinical decision-making. Therefore, we have incorporated an effective uncertainty estimation method based on Monte Carlo Dropout into our model. Furthermore, we have employed temperature scaling to calibrate the predictions of our probabilistic model, enhancing its reliability. In experiments conducted on the CirCor Digiscope dataset for heart murmur detection, our proposed method achieves a weighted accuracy of 79.8% and an F1 of 65.1%, representing state-of-the-art results.

Adaptive Speech Emotion Representation Learning Based On Dynamic Graph

Graph representation learning has become a hot research topic due to its powerful nonlinear fitting capability in extracting representative node embeddings. However, for sequential data such as speech signals, most traditional methods merely focus on the static graph created within a sequence, and largely overlook the intrinsic evolving patterns of these data. This may reduce the efficiency of graph representation learning for sequential data. For this reason, we propose an adaptive graph representation learning method based on dynamically evolved graphs, which are consecutively constructed on a series of subsequences segmented by a sliding window. In doing this, it is better to capture local and global context information within a long sequence. Moreover, we introduce a weighted approach to update the node representation rather than the conventional average one, where the weights are calculated by a novel matrix computation based on the degree of neighboring nodes. Finally, we construct a learnable graph convolutional layer that combines the graph structure loss and classification loss to optimize the graph structure. To verify the effectiveness of the proposed method, we conducted experiments for speech emotion recognition on the IEMOCAP and RAVDESS datasets. Experimental results show that the proposed method outperforms the latest (non-)graph-based models.

STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition

Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction. The robustness of SER models is crucial, particularly in privacy-sensitive and reliability-demanding domains like private healthcare. Recently, the vulnerability of deep neural networks in the audio domain to adversarial attacks has become a popular area of research. However, prior works on adversarial attacks in the audio domain primarily rely on iterative gradient-based techniques, which are time-consuming and prone to overfitting the specific threat model. Furthermore, the exploration of sparse perturbations, which have the potential for better stealthiness, remains limited in the audio domain. To address these challenges, we propose a generator-based attack method to generate sparse and transferable adversarial examples to deceive SER models in an end-to-end and efficient manner. We evaluate our method on two widely-used SER datasets, Database of Elicited Mood in Speech (DEMoS) and Interactive Emotional dyadic MOtion CAPture (IEMOCAP), and demonstrate its ability to generate successful sparse adversarial examples in an efficient manner. Moreover, our generated adversarial examples exhibit model-agnostic transferability, enabling effective adversarial attacks on advanced victim models.