Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that fuses deep semantic embeddings from the Whisper encoder with an interpretable acoustic feature vector composed of eGeMAPS descriptors and auxiliary probability estimates of vocal stress and disfluency. To mitigate reliance on scarce ground truth data, we introduce an Uncertainty-Aware Pseudo-Labelling strategy where a model generates labels for unlabelled data, retaining only high-quality samples for training. Experimental results demonstrate that the proposed approach achieves a Macro-F1 score of 0.751, outperforming self-supervised baselines, including WavLM, HuBERT, and Wav2Vec 2.0. The hybrid architecture also surpasses the unimodal Whisper baseline, yielding a 3\% improvement in the minority class, confirming that explicit prosodic and auxiliary features provide necessary corrective signals which are otherwise lost in deep semantic representations. Ablation studies further show that a curated set of high confidence pseudo-labels outperforms indiscriminate large scale augmentation, confirming that data quality outweighs quantity for perceived confidence detection.

Singing Voice Conversion (SVC) aims to transform a source singing voice into a target singer while preserving lyrics and melody. Most existing SVC methods depend on F0 extractors to capture the lead melody from clean vocals. However, no existing method can reliably extract clean vocals from accompanied recordings without leaving residual harmonies behind. In this paper, we innovatively propose Poly-SVC, a zero-shot, cross-lingual singing voice conversion system designed to process residual harmonies. Poly-SVC is composed of three key components: a Constant-Q Transform (CQT)-based pitch extractor to preserve both the lead melody and residual harmony, a random sampler to reduce interference information from the CQT and a diffusion decoder based on Conditional Flow Matching (CFM) that fuses pitch, content, and timbre features into natural-sounding polyphonic outputs. Experiments demonstrate that Poly-SVC surpasses the baseline models in naturalness, timbre similarity and harmony reconstruction across both harmony-rich and single-melody recordings.

Over the past two decades, the task of musical beat tracking has transitioned from heuristic onset detection algorithms to highly capable deep neural networks (DNN). Although DNN-based beat tracking models achieve near-perfect performance on mainstream, percussive datasets, the SMC dataset has stubbornly yielded low F-measure scores. By testing how well state-of-the-art models detect beats on individual tracks in the SMC dataset, we identify three distinct failure modes: octave errors, continuity errors, and complete tracking failure where all metrics fall below 0.3. We reveal that state-of-the-art models tend to generate "confident-but-wrong" activations. Furthermore, we show that the standard DBN's default minimum tempo of 55 BPM prevents it from inferring the correct tempo for 21\% of SMC tracks, forcing double-tempo predictions on slow music. By exposing such fundamental oversights, we provide concrete directions for improving beat and downbeat detection, specifically emphasizing training data diversification and multi-hypothesis tempo estimation.

We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone Hero / YARG charts for drums, guitar, bass, vocals, and keys without any oracle metadata. STRUM is a multi-stage hybrid: a two-stage CRNN onset detector and a six-model ensemble classifier for drums; neural onset detectors with monophonic pitch tracking for guitar and bass; word-aligned ASR for vocals; and spectral keyboard detection for keys. We evaluate on a 30-song in-envelope benchmark constructed by screening candidate songs on a single audio-quality criterion -- the median 1-second drum-stem RMS after htdemucs_6s source separation. On this benchmark STRUM achieves drums onset F1 = 0.838, bass F1 = 0.694, guitar F1 = 0.651, and vocals F1 = 0.539 at a +/- 100 ms tolerance with per-song global offset search. We report a complete ablation of seven drum-pipeline components with paired per-song Wilcoxon tests, an analysis of ground-truth-to-audio timing distributions in community Clone Hero charts, and a per-class confusion matrix for the drum classifier. Code, model weights, and the full benchmark manifest are released.

Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.g., mood, location, or social setting). In this paper, we introduce a Large Language Model (LLM)-based alternative that maps natural language text prompts to equalization settings. This enables a conversational approach to sound system control. By utilizing data collected from a controlled listening experiment, our models exploit in-context learning and parameter-efficient fine-tuning techniques to reliably align with population-preferred equalization settings. Our evaluation methods, which leverage distributional metrics that capture users' varied preferences, show statistically significant improvements in distributional alignment over random sampling and static preset baselines. These results indicate that LLMs could function as "artificial equalizers," contributing to the development of more accessible, context-aware, and expert-level audio tuning methods.

Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing significant challenges due to the complexity of semantic modeling and the scarcity of CS data. Previous studies mainly rely on the models themselves to implicitly learn semantic representations and resort to costly manual annotations. To mitigate these limitations, we propose enhancing Large Language Models (LLMs) with a Mixture-of-Experts (MoE) speech projector composed of language expert groups, where each group specializes in the semantic space of a specific language for fine-grained speech feature modeling. A language-specific loss and an intra-group load balancing loss are jointly introduced to guide efficient token routing across and within expert groups. Furthermore, we introduce a multi-stage training paradigm that utilizes readily available automatic speech recognition (ASR) and monolingual ST data, facilitating speech-text alignment and improving translation performance. To bridge the data gap for smooth domain transfer, a transition loss is employed to improve adaptation to CS scenarios. Extensive experiments on widely used datasets demonstrate the effectiveness and generality of our approach, achieving average improvements of $0.86$ BLEU and $0.93$ COMET over SeamlessM4T, with maximum improvements of $1.49$ BLEU and $1.41$ COMET across different test sets.

We propose a novel mixture of experts framework for field-of-view enhancement in binaural signal matching. Our approach enables dynamic spatial audio rendering that adapts to continuous talker motion, allowing users to emphasize or suppress sounds from selected directions while preserving natural binaural cues. Unlike traditional methods that rely on explicit direction-of-arrival estimation or operate in the Ambisonics domain, our signal-dependent framework combines multiple binaural filters in an online manner using implicit localization. This allows for real-time tracking and enhancement of moving sound sources, supporting applications such as speech focus, noise reduction, and world-locked audio in augmented and virtual reality. The method is agnostic to array geometry offering a flexible solution for spatial audio capture and personalized playback in next-generation consumer audio devices.

In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with inconsistent modalities (image, audio, or video) and varying task types (captioning or question-answering). Unlike existing vision-only or modality-incremental settings, MICL combines modality and task type shifts, both of which drive catastrophic forgetting. To address these challenges, we propose MoInCL, which employs a Pseudo Targets Generation Module to mitigate forgetting caused by task type shifts in previously seen modalities. It also incorporates Instruction-based Knowledge Distillation to preserve the model's ability to handle previously learned modalities when new ones are introduced. We benchmark MICL using a total of six tasks and conduct experiments to validate the effectiveness of our MoInCL. The experimental results highlight the superiority of MoInCL, showing significant improvements over representative and state-of-the-art continual learning baselines.

Reliable adaptive beamforming is critical for large microphone arrays operating in highly dynamic acoustic environments. In scenarios characterized by fast-moving talkers and interferers, the available sample support for estimating the spatial correlation matrix is often snapshot-deficient. This deficiency degrades the White Noise Gain (WNG), leading to severe target signal cancellation. To ensure stable and robust beamforming, we previously proposed an adaptive diagonal loading method that leverages the Kantorovich inequality to guarantee the WNG remains strictly within specified bounds. However, accurately determining the smallest necessary loading level requires calculating the extreme eigenvalues of the spatial correlation matrix, a computationally expensive $\mathcal{O}(M^3)$ operation for large arrays. In this paper, we introduce a highly efficient $\mathcal{O}(kM^2)$ estimation technique using Lanczos iterations to build a small Krylov subspace. By projecting the correlation matrix onto a tridiagonal matrix of dimension $k \ll M$, we extract Ritz values that rapidly converge to the exact extreme eigenvalues. Our evaluations demonstrate that this Lanczos-accelerated approach achieves performance identical to exact Eigenvalue Decomposition (EVD), ensuring optimal interference suppression and strict WNG adherence at a fraction of the computational cost.

Neural audio codecs provide compact discrete representations for speech generation and manipulation. However, most codecs organize tokens as frame-level sequences, making it difficult to study or intervene on global factors of variation. In this work, we propose the Latent Audio Tokenizer for Token-space Editing (LATTE) that appends a fixed set of learnable latent tokens to the audio feature sequence and retains only these tokens for quantization and decoding. This design produces a compact, non-temporally aligned bottleneck in which each token can aggregate global information across the full utterance. We show that the resulting tokenizer preserves competitive reconstruction quality in low-bitrate speech coding settings while enabling simple token-space interventions. In particular, we find that swapping selected latent token positions between utterances can modify global attributes, such as speaker identity and background noise, and we evaluate these interventions on voice conversion and denoising tasks. Our results suggest that compact latent audio tokenizers can support controllable audio manipulation without supervision in task-specific editing models.

Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acoustic reconstruction, leaving emotion expressiveness insufficiently modeled at the representation level. We propose an emotion-guided neural speech codec that explicitly preserves emotional information while maintaining semantic fidelity and prosodic naturalness. Our framework combines emotion-semantic guided latent modulation, relation-preserving emotional-semantic distillation, and emotion-weighted semantic alignment to retain emotionally salient cues under compression. Extensive evaluations across speech reconstruction, emotion recognition, and downstream text-to-speech generation demonstrate improved emotion consistency and perceptual quality without sacrificing content accuracy.

Robust spatial audio control relies on accurate acoustic propagation models, yet environmental variations, especially changes in the speed of sound, cause systematic mismatches that degrade performance. Existing methods either assume known sound speed, require multiple microphones, or rely on separate calibration, making them impractical for systems with minimal sensing. We propose an online sound speed estimator that operates during general multichannel audio playback and requires only a single observation microphone. The method exploits the structured effect of sound speed on the reproduced signal and estimates it by minimizing the mismatch between the measured audio and a parametric acoustic model. Simulations show accurate tracking of sound speed for diverse input signals and improved spatial control performance when the estimates are used to compensate propagation errors in a sound zone control framework.

COVID-19 has affected more than 223 countries worldwide and in the Post-COVID Era, there is a pressing need for non-invasive, low-cost, and highly scalable solutions to detect COVID-19. We develop a deep learning model to identify COVID-19 from voice recording data. The novelty of this work is in the development of deep learning models for COVID-19 identification from only voice recordings. We use the Cambridge COVID-19 Sound database which contains 893 speech samples, crowd-sourced from 4352 participants via a COVID-19 Sounds app. Voice features including Mel-spectrograms and Mel-frequency cepstral coefficients (MFCC) and CNN Encoder features are extracted. Based on the voice data, we develop deep learning classification models to detect COVID-19 cases. These models include Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) and Hidden-Unit BERT (HuBERT). We compare their predictive power to baseline machine learning models. HuBERT achieves the highest accuracy of 86\% and the highest AUC of 0.93. The results achieved with the proposed models suggest promising results in COVID-19 diagnosis from voice recordings when compared to the results obtained from the state-of-the-art.