Achieving high-fidelity audio compression while preserving perceptual quality across diverse audio types remains a significant challenge in Neural Audio Coding (NAC). This paper introduces MUFFIN, a fully convolutional NAC framework that leverages psychoacoustically guided multi-band frequency reconstruction. Central to MUFFIN is the Multi-Band Spectral Residual Vector Quantization (MBS-RVQ) mechanism, which quantizes latent speech across different frequency bands. This approach optimizes bitrate allocation and enhances fidelity based on psychoacoustic studies, achieving efficient compression with unique perceptual features that separate content from speaker attributes through distinct codebooks. MUFFIN integrates a transformer-inspired convolutional architecture with proposed modified snake activation functions to capture fine frequency details with greater precision. Extensive evaluations on diverse datasets (LibriTTS, IEMOCAP, GTZAN, BBC) demonstrate MUFFIN’s ability to consistently surpass existing performance in audio reconstruction across various domains. Notably, a high-compression variant achieves an impressive SOTA 12.5 kHz rate while preserving reconstruction quality. Furthermore, MUFFIN excels in downstream generative tasks, demonstrating its potential as a robust token representation for integration with large language models. These results establish MUFFIN as a groundbreaking advancement in NAC and as the first neural psychoacoustic coding system. Speech demos and codes are available at https://demos46.github.io/muffin/ and https://github.com/dianwen-ng/MUFFIN.

Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing portability while also maintaining competitive performance. However, not many people understand how and why this is so. In this study, we aim to deepen our understanding of this emerging method by investigating the role of soft prompts in automatic speech recognition (ASR). Our findings highlight their role as zero-shot learners in improving ASR performance while also exposing them to the risk of malicious modifications. Soft prompts aid generalization but are not obligatory for inference. We also identify two primary roles of soft prompts: content refinement and noise information enhancement, which enhances robustness against background noise. Additionally, we propose an effective modification on noise prompts to show that they are capable of zero-shot learning on adapting to out-of-distribution noise environments.

Dual-path is a popular architecture for speech separation models (e.g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships. However, it has been found that inter-blocks, which comprise half a dual-path model’s parameters, contribute minimally to performance. Thus, we propose the Single-Path Global Modulation (SPGM) block to replace inter-blocks. SPGM is named after its structure consisting of a parameter-free global pooling module followed by a modulation module comprising only 2% of the model’s total parameters. The SPGM block allows all transformer layers in the model to be dedicated to local feature modelling, making the overall model single-path. SPGM achieves 22.1 dB SI-SDRi on WSJ0-2Mix and 20.4 dB SI-SDRi on Libri2Mix, exceeding the performance of Sepformer by 0.5 dB and 0.3 dB respectively and matches the performance of recent SOTA models with up to 8 times fewer parameters. Model and weights are available at huggingface.co/yipjiaqi/spgm

Our previously proposed MossFormer has achieved promising performance in monaural speech separation. However, it predominantly adopts a self-attention-based MossFormer module, which tends to emphasize longer-range, coarser-scale dependencies, with a deficiency in effectively modelling finer-scale recurrent patterns. In this paper, we introduce a novel hybrid model that provides the capabilities to model both long-range, coarse-scale dependencies and fine-scale recurrent patterns by integrating a recurrent module into the MossFormer framework. Instead of applying the recurrent neural networks (RNNs) that use traditional recurrent connections, we present a recurrent module based on a feedforward sequential memory network (FSMN), which is considered "RNN-free" recurrent network due to the ability to capture recurrent patterns without using recurrent connections. Our recurrent module mainly comprises an enhanced dilated FSMN block by using gated convolutional units (GCU) and dense connections. In addition, a bottleneck layer and an output layer are also added for controlling information flow. The recurrent module relies on linear projections and convolutions for seamless, parallel processing of the entire sequence. The integrated MossFormer2 hybrid model demonstrates remarkable enhancements over MossFormer and surpasses other state-of-the-art methods in WSJ0-2/3mix, Libri2Mix, and WHAM!/WHAMR! benchmarks.

In multi-modal emotion recognition, previous studies focus on obtaining more distinguishable unimodal features and expanding complementary information across modalities. However, a considerable amount of latent emotional information is neglected. It leads to insufficient intra-modal representations and a one-sided perspective on inter-modal relationship learning. To address these challenges, we propose a novel framework named MRFER, which explores strategies to reduce the loss of emotional information. It models robust unimodal features through a multi-path feature extractor and captures more comprehensive inter-modal relationships through a text-guided dual attention fusion module. Systematic evaluation covers generalization and overall performance, showcasing MRFER’s advancement beyond existing state-of-the-art approaches.

Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a single source, which tends to do poorly when noise is present during testing. Nonetheless, it is crucial to overcome the adverse influence of noise for real-world applications. In this work, we propose a novel training framework, called deHuBERT, for noise reduction encoding inspired by H. Barlow’s redundancy-reduction principle. The new framework improves the HuBERT training algorithm by introducing auxiliary losses that drive the self- and cross-correlation matrix between pairwise noise-distorted embeddings towards identity matrix. This encourages the model to produce noise- agnostic speech representations. With this method, we report improved robustness in noisy environments, including unseen noises, without impairing the performance on the clean set.

Most of the existing neural-based models for keyword spotting (KWS) in smart devices require thousands of training samples to learn a decent audio representation. However, with the rising demand for smart devices to become more person-alized, KWS models need to adapt quickly to smaller user samples. To tackle this challenge, we propose a contrastive speech mixup (CosMix) learning algorithm for low-resource KWS. CosMix introduces an auxiliary contrastive loss to the existing mixup augmentation technique to maximize the relative similarity between the original pre-mixed samples and the augmented samples. The goal is to inject enhancing constraints to guide the model towards simpler but richer content-based speech representations from two augmented views (i.e. noisy mixed and clean pre-mixed utterances). We conduct our experiments on the Google Speech Command dataset, where we trim the size of the training set to as small as 2.5 mins per keyword to simulate a low-resource condition. Our experimental results show a consistent improvement in the performance of multiple models, which exhibits the effectiveness of our method.

Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however, is challenging due to the modal disparity between textual and speech embedding spaces. This paper studies metric-based distillation to align the embedding space of text and speech with only a small amount of data without modifying the model structure. Since the semantic and granularity gap between text and speech has been omitted in literature, which impairs the distillation, we propose the Prior-informed Adaptive knowledge Distillation (PAD) that adaptively leverages text/speech units of variable granularity and prior distributions to achieve better global and local alignments between text and speech pre-trained models. We evaluate on three spoken language understanding benchmarks to show that PAD is more effective in transferring linguistic knowledge than other metric-based distillation approaches.

Learning information-rich and generalizable representations effectively from unlabeled multivariate cardiac signals to identify abnormal heart rhythms (cardiac arrhythmias) is valuable in real-world clinical settings but often challenging due to its complex temporal dynamics. Cardiac arrhythmias can vary significantly in temporal patterns even for the same patient (i.e., intra subject difference). Meanwhile, the same type of cardiac arrhythmia can show different temporal patterns among different patients due to different cardiac structures (i.e., inter subject difference). In this paper, we address the challenges by proposing an Intra-Inter Subject Self-Supervised Learning (ISL) model that is customized for multivariate cardiac signals. Our proposed ISL model integrates medical knowledge into self-supervision to effectively learn from intra-inter subject differences. In intra subject self-supervision, ISL model first extracts heartbeat-level features from each subject using a channel-wise attentional CNN-RNN encoder. Then a stationarity test module is employed to capture the temporal dependencies between heartbeats. In inter subject self-supervision, we design a set of data augmentations according to the clinical characteristics of cardiac signals and perform contrastive learning among subjects to learn distinctive representations for various types of patients. Extensive experiments on three real-world datasets were conducted. In a semi-supervised transfer learning scenario, our pre-trained ISL model leads about 10% improvement over supervised training when only 1% labeled data is available, suggesting strong generalizability and robustness of the model.

Building efficient architecture in neural speech processing is paramount to success in keyword spotting deployment. However, it is very challenging for lightweight models to achieve noise robustness with concise neural operations. In a real-world application, the user environment is typically noisy and may contain reverberations. We proposed a novel feature interactive convolutional model with merely 100K parameters to tackle this under the noisy far-field condition. The interactive unit is proposed in place of the attention module that promotes the flow of information with more efficient computations. Moreover, curriculum-based multi-condition training is adopted to attain better noise robustness. Our model achieves 98.2% top-1 accuracy on Google Speech Command V2-12 and is competitive against large transformer models under the designed noise condition.

Disk fault is known to be the key cause of data loss in the modern large-scale data center, which affects the reliability and stability of the server and even the whole IT infrastructure, resulting in high financial cost. Recent works on disk fault prediction demonstrate the ability of machine learning techniques in the early prediction of disk failure. However, two limitations hinder the real-world application of current methods. First, they ignore the data heterogeneity in the data center, where distribution shifts commonly exist across different disk model types that decrease the model's performance. Second, the number of disks of different disk model types varies greatly in the data center, and current methods failed to deliver an acceptable performance over disk model types with few training samples. To address these limitations, we propose adversarial domain adaptation with correlation-based association networks (ADA-CBAN) to both mitigate the distribution shift problem and also to boost the performance on small-scaled data. Extensive experiments prove that our proposed model is effective and achieves new state-of-the-art. In addition, our post model analysis can also reveal important feature interactions and highlight the crucial period before disk faults, where both are useful information in real-world applications.