OneVoice: One Model, Triple Scenarios-Towards Unified Zero-shot Voice Conversion

Recent progress of voice conversion~(VC) has achieved a new milestone in speaker cloning and linguistic preservation. But the field remains fragmented, relying on specialized models for linguistic-preserving, expressive, and singing scenarios. We propose OneVoice, a unified zero-shot framework capable of handling all three scenarios within a single model. OneVoice is built upon a continuous language model trained with VAE-free next-patch diffusion, ensuring high fidelity and efficient sequence modeling. Its core design for unification lies in a Mixture-of-Experts (MoE) designed to explicitly model shared conversion knowledge and scenario-specific expressivity. Expert selection is coordinated by a dual-path routing mechanism, including shared expert isolation and scenario-aware domain expert assignment with global-local cues. For precise conditioning, scenario-specific prosodic features are fused into each layer via a gated mechanism, allowing adaptive usage of prosody information. Furthermore, to enable the core idea and alleviate the imbalanced issue (abundant speech vs. scarce singing), we adopt a two-stage progressive training that includes foundational pre-training and scenario enhancement with LoRA-based domain experts. Experiments show that OneVoice matches or surpasses specialized models across all three scenarios, while verifying flexible control over scenarios and offering a fast decoding version as few as 2 steps. Code and model will be released soon.

From Human Speech to Ocean Signals: Transferring Speech Large Models for Underwater Acoustic Target Recognition

Underwater acoustic target recognition (UATR) plays a vital role in marine applications but remains challenging due to limited labeled data and the complexity of ocean environments. This paper explores a central question: can speech large models (SLMs), trained on massive human speech corpora, be effectively transferred to underwater acoustics? To investigate this, we propose UATR-SLM, a simple framework that reuses the speech feature pipeline, adapts the SLM as an acoustic encoder, and adds a lightweight classifier.Experiments on the DeepShip and ShipsEar benchmarks show that UATR-SLM achieves over 99% in-domain accuracy, maintains strong robustness across variable signal lengths, and reaches up to 96.67% accuracy in cross-domain evaluation. These results highlight the strong transferability of SLMs to UATR, establishing a promising paradigm for leveraging speech foundation models in underwater acoustics.

Unheard in the Digital Age: Rethinking AI Bias and Speech Diversity

Speech remains one of the most visible yet overlooked vectors of inclusion and exclusion in contemporary society. While fluency is often equated with credibility and competence, individuals with atypical speech patterns are routinely marginalized. Given the current state of the debate, this article focuses on the structural biases that shape perceptions of atypical speech and are now being encoded into artificial intelligence. Automated speech recognition (ASR) systems and voice interfaces, trained predominantly on standardized speech, routinely fail to recognize or respond to diverse voices, compounding digital exclusion. As AI technologies increasingly mediate access to opportunity, the study calls for inclusive technological design, anti-bias training to minimize the impact of discriminatory algorithmic decisions, and enforceable policy reform that explicitly recognize speech diversity as a matter of equity, not merely accessibility. Drawing on interdisciplinary research, the article advocates for a cultural and institutional shift in how we value voice, urging co-created solutions that elevate the rights, representation, and realities of atypical speakers in the digital age. Ultimately, the article reframes speech inclusion as a matter of equity (not accommodation) and advocates for co-created AI systems that reflect the full spectrum of human voices.

BanglaRobustNet: A Hybrid Denoising-Attention Architecture for Robust Bangla Speech Recognition

Bangla, one of the most widely spoken languages, remains underrepresented in state-of-the-art automatic speech recognition (ASR) research, particularly under noisy and speaker-diverse conditions. This paper presents BanglaRobustNet, a hybrid denoising-attention framework built on Wav2Vec-BERT, designed to address these challenges. The architecture integrates a diffusion-based denoising module to suppress environmental noise while preserving Bangla-specific phonetic cues, and a contextual cross-attention module that conditions recognition on speaker embeddings for robustness across gender, age, and dialects. Trained end-to-end with a composite objective combining CTC loss, phonetic consistency, and speaker alignment, BanglaRobustNet achieves substantial reductions in word error rate (WER) and character error rate (CER) compared to Wav2Vec-BERT and Whisper baselines. Evaluations on Mozilla Common Voice Bangla and augmented noisy speech confirm the effectiveness of our approach, establishing BanglaRobustNet as a robust ASR system tailored to low-resource, noise-prone linguistic settings.

Quran-MD: A Fine-Grained Multilingual Multimodal Dataset of the Quran

We present Quran MD, a comprehensive multimodal dataset of the Quran that integrates textual, linguistic, and audio dimensions at the verse and word levels. For each verse (ayah), the dataset provides its original Arabic text, English translation, and phonetic transliteration. To capture the rich oral tradition of Quranic recitation, we include verse-level audio from 32 distinct reciters, reflecting diverse recitation styles and dialectical nuances. At the word level, each token is paired with its corresponding Arabic script, English translation, transliteration, and an aligned audio recording, allowing fine-grained analysis of pronunciation, phonology, and semantic context. This dataset supports various applications, including natural language processing, speech recognition, text-to-speech synthesis, linguistic analysis, and digital Islamic studies. Bridging text and audio modalities across multiple reciters, this dataset provides a unique resource to advance computational approaches to Quranic recitation and study. Beyond enabling tasks such as ASR, tajweed detection, and Quranic TTS, it lays the foundation for multimodal embeddings, semantic retrieval, style transfer, and personalized tutoring systems that can support both research and community applications. The dataset is available at https://huggingface.co/datasets/Buraaq/quran-audio-text-dataset

AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking

Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examine whether AI models can understand such signals in human cultural contexts, we introduce AVMeme Exam, a human-curated benchmark of over one thousand iconic Internet sounds and videos spanning speech, songs, music, and sound effects. Each meme is paired with a unique Q&A assessing levels of understanding from surface content to context and emotion to usage and world knowledge, along with metadata such as original year, transcript, summary, and sensitivity. We systematically evaluate state-of-the-art multimodal large language models (MLLMs) alongside human participants using this benchmark. Our results reveal a consistent limitation: current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content. These findings highlight a key gap in human-aligned multimodal intelligence and call for models that can perceive contextually and culturally beyond the surface of what they hear and see. Project page: avmemeexam.github.io/public

AmbER$^2$: Dual Ambiguity-Aware Emotion Recognition Applied to Speech and Text

Emotion recognition is inherently ambiguous, with uncertainty arising both from rater disagreement and from discrepancies across modalities such as speech and text. There is growing interest in modeling rater ambiguity using label distributions. However, modality ambiguity remains underexplored, and multimodal approaches often rely on simple feature fusion without explicitly addressing conflicts between modalities. In this work, we propose AmbER$^2$, a dual ambiguity-aware framework that simultaneously models rater-level and modality-level ambiguity through a teacher-student architecture with a distribution-wise training objective. Evaluations on IEMOCAP and MSP-Podcast show that AmbER$^2$ consistently improves distributional fidelity over conventional cross-entropy baselines and achieves performance competitive with, or superior to, recent state-of-the-art systems. For example, on IEMOCAP, AmbER$^2$ achieves relative improvements of 20.3% on Bhattacharyya coefficient (0.83 vs. 0.69), 13.6% on R$^2$ (0.67 vs. 0.59), 3.8% on accuracy (0.683 vs. 0.658), and 4.5% on F1 (0.675 vs. 0.646). Further analysis across ambiguity levels shows that explicitly modeling ambiguity is particularly beneficial for highly uncertain samples. These findings highlight the importance of jointly addressing rater and modality ambiguity when building robust emotion recognition systems.

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows linearly with sequence length. Meanwhile, discrete diffusion large language models (dLLMs) offer a promising alternative, enabling high-quality parallel sequence generation with pretrained decoders. However, directly applying native text-oriented dLLMs to ASR leads to a fundamental mismatch between open-ended text generation and the acoustically conditioned transcription paradigm required by ASR. As a result, it introduces unnecessary difficulty and computational redundancy, such as denoising from pure noise, inflexible generation lengths, and fixed denoising steps. We propose dLLM-ASR, an efficient dLLM-based ASR framework that formulates dLLM's decoding as a prior-guided and adaptive denoising process. It leverages an ASR prior to initialize the denoising process and provide an anchor for sequence length. Building upon this prior, length-adaptive pruning dynamically removes redundant tokens, while confidence-based denoising allows converged tokens to exit the denoising loop early, enabling token-level adaptive computation. Experiments demonstrate that dLLM-ASR achieves recognition accuracy comparable to autoregressive LLM-based ASR systems and delivers a 4.44$\times$ inference speedup, establishing a practical and efficient paradigm for ASR.

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation

Real-world perception and interaction are inherently multimodal, encompassing not only language but also vision and speech, which motivates the development of "Omni" MLLMs that support both multimodal inputs and multimodal outputs. While a sequence of omni MLLMs has emerged, most existing systems still rely on additional expert components to achieve multimodal generation, limiting the simplicity of unified training and inference. Autoregressive (AR) modeling, with a single token stream, a single next-token objective, and a single decoder, is an elegant and scalable foundation in the text domain. Motivated by this, we present AR-Omni, a unified any-to-any model in the autoregressive paradigm without any expert decoders. AR-Omni supports autoregressive text and image generation, as well as streaming speech generation, all under a single Transformer decoder. We further address three practical issues in unified AR modeling: modality imbalance via task-aware loss reweighting, visual fidelity via a lightweight token-level perceptual alignment loss for image tokens, and stability-creativity trade-offs via a finite-state decoding mechanism. Empirically, AR-Omni achieves strong quality across three modalities while remaining real-time, achieving a 0.88 real-time factor for speech generation.

SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays

Spatial information is a critical clue for multi-channel multi-speaker target speech recognition. Most state-of-the-art multi-channel Automatic Speech Recognition (ASR) systems extract spatial features only during the speech separation stage, followed by standard single-channel ASR on the separated speech. This approach results in an inefficient, lengthy pipeline and sub-optimal ASR performance due to the accumulated errors from preprocessing modules. Furthermore, most spatial feature extraction methods depend on the knowledge of speaker positions and microphone topology, making the systems reliant on specific settings and challenging to adapt to new equipment. In this work, we propose a solution to these issues with a lightweight embedding module named SpatialEmb, which extracts and encodes spatial information directly for the ASR model, supporting both fixed and arbitrary microphone topology. We conduct comprehensive experiments on AliMeeting, a real meeting corpus, to determine the optimal model design for SpatialEmb in terms of both performance and efficiency. Our best model trained with 105 hours Train-Ali-far achieves 17.04% and 20.32% character error rates (CER) on the Eval and Test sets, establishing a new state-of-the-art result with the same training data.