The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset

The advance of speech decoding from non-invasive brain data holds the potential for profound societal impact. Among its most promising applications is the restoration of communication to paralysed individuals affected by speech deficits such as dysarthria, without the need for high-risk surgical interventions. The ultimate aim of the 2025 PNPL competition is to produce the conditions for an "ImageNet moment" or breakthrough in non-invasive neural decoding, by harnessing the collective power of the machine learning community. To facilitate this vision we present the largest within-subject MEG dataset recorded to date (LibriBrain) together with a user-friendly Python library (pnpl) for easy data access and integration with deep learning frameworks. For the competition we define two foundational tasks (i.e. Speech Detection and Phoneme Classification from brain data), complete with standardised data splits and evaluation metrics, illustrative benchmark models, online tutorial code, a community discussion board, and public leaderboard for submissions. To promote accessibility and participation the competition features a Standard track that emphasises algorithmic innovation, as well as an Extended track that is expected to reward larger-scale computing, accelerating progress toward a non-invasive brain-computer interface for speech.

FedMLAC: Mutual Learning Driven Heterogeneous Federated Audio Classification

Federated Learning (FL) provides a privacy-preserving paradigm for training audio classification (AC) models across distributed clients without sharing raw data. However, Federated Audio Classification (FedAC) faces three critical challenges that substantially hinder performance: data heterogeneity, model heterogeneity, and data poisoning. While prior works have attempted to address these issues, they are typically treated independently, lacking a unified and robust solution suited to real-world federated audio scenarios. To bridge this gap, we propose FedMLAC, a unified mutual learning framework designed to simultaneously tackle these challenges in FedAC. Specifically, FedMLAC introduces a dual-model architecture on each client, comprising a personalized local AC model and a lightweight, globally shared Plug-in model. Through bidirectional knowledge distillation, the Plug-in model enables global knowledge transfer while adapting to client-specific data distributions, thus supporting both generalization and personalization. To further enhance robustness against corrupted audio data, we develop a Layer-wise Pruning Aggregation (LPA) strategy that filters unreliable Plug-in model updates based on parameter deviations during server-side aggregation. Extensive experiments on four diverse audio classification benchmarks, spanning both speech and non-speech tasks, demonstrate that FedMLAC consistently outperforms existing state-of-the-art methods in terms of classification accuracy and robustness to noisy data.

A Study on Speech Assessment with Visual Cues

Non-intrusive assessment of speech quality and intelligibility is essential when clean reference signals are unavailable. In this work, we propose a multimodal framework that integrates audio features and visual cues to predict PESQ and STOI scores. It employs a dual-branch architecture, where spectral features are extracted using STFT, and visual embeddings are obtained via a visual encoder. These features are then fused and processed by a CNN-BLSTM with attention, followed by multi-task learning to simultaneously predict PESQ and STOI. Evaluations on the LRS3-TED dataset, augmented with noise from the DEMAND corpus, show that our model outperforms the audio-only baseline. Under seen noise conditions, it improves LCC by 9.61% (0.8397->0.9205) for PESQ and 11.47% (0.7403->0.8253) for STOI. These results highlight the effectiveness of incorporating visual cues in enhancing the accuracy of non-intrusive speech assessment.

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary

Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words. While contextual biasing (CB) is a promising approach to improve recognition of such words, most CB methods are trained from scratch, resulting in lower performance than SFMs due to the lack of pre-trained knowledge. This paper integrates an existing CB method with OWSM v3.1 while freezing its pre-trained parameters. By leveraging the knowledge embedded in SFMs, the proposed method enables effective CB while preserving the advantages of SFMs, even with a small dataset. Experimental results show that the proposed method improves the biasing word error rate (B-WER) by 11.6 points, resulting in a 0.9 point improvement in the overall WER while reducing the real-time factor by 7.5% compared to the non-biasing baseline on the LibriSpeech 100 test-clean set.

Ming-Omni: A Unified Multimodal Model for Perception and Generation

We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single model to efficiently process and fuse multimodal inputs within a unified framework, thereby facilitating diverse tasks without requiring separate models, task-specific fine-tuning, or structural redesign. Importantly, Ming-Omni extends beyond conventional multimodal models by supporting audio and image generation. This is achieved through the integration of an advanced audio decoder for natural-sounding speech and Ming-Lite-Uni for high-quality image generation, which also allow the model to engage in context-aware chatting, perform text-to-speech conversion, and conduct versatile image editing. Our experimental results showcase Ming-Omni offers a powerful solution for unified perception and generation across all modalities. Notably, our proposed Ming-Omni is the first open-source model we are aware of to match GPT-4o in modality support, and we release all code and model weights to encourage further research and development in the community.

Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction

Audio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others. We know that humans leverage linguistic knowledge, such as syntax and semantics, to support speech perception. Inspired by this, we explore the potential of pre-trained speech-language models (PSLMs) and pre-trained language models (PLMs) as auxiliary knowledge sources for AV-TSE. In this study, we propose incorporating the linguistic constraints from PSLMs or PLMs for the AV-TSE model as additional supervision signals. Without introducing any extra computational cost during inference, the proposed approach consistently improves speech quality and intelligibility. Furthermore, we evaluate our method in multi-language settings and visual cue-impaired scenarios and show robust performance gains.

Recognizing Every Voice: Towards Inclusive ASR for Rural Bhojpuri Women

Digital inclusion remains a challenge for marginalized communities, especially rural women in low-resource language regions like Bhojpuri. Voice-based access to agricultural services, financial transactions, government schemes, and healthcare is vital for their empowerment, yet existing ASR systems for this group remain largely untested. To address this gap, we create SRUTI ,a benchmark consisting of rural Bhojpuri women speakers. Evaluation of current ASR models on SRUTI shows poor performance due to data scarcity, which is difficult to overcome due to social and cultural barriers that hinder large-scale data collection. To overcome this, we propose generating synthetic speech using just 25-30 seconds of audio per speaker from approximately 100 rural women. Augmenting existing datasets with this synthetic data achieves an improvement of 4.7 WER, providing a scalable, minimally intrusive solution to enhance ASR and promote digital inclusion in low-resource language.

Improved in-car sound pick-up using multichannel Wiener filter

With advancements in automotive electronics and sensors, the sound pick-up using multiple microphones has become feasible for hands-free telephony and voice command in-car applications. However, challenges remain in effectively processing multiple microphone signals due to bandwidth or processing limitations. This work explores the use of the Multichannel Wiener Filter algorithm with a two-microphone in-car system, to enhance speech quality for driver and passenger voice, i.e., to mitigate notch-filtering effects caused by echoes and improve background noise reduction. We evaluate its performance under various noise conditions using modern objective metrics like Deep Noise Suppression Mean Opinion Score. The effect of head movements of driver/passenger is also investigated. The proposed method is shown to provide significant improvements over a simple mixing of microphone signals.

Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval

Recent approaches have shown impressive proficiency in extracting and leveraging parametric knowledge from Large-Language Models (LLMs) and Vision-Language Models (VLMs). In this work, we consider how we can improve the identification and retrieval of videos related to complex real-world events by automatically extracting latent parametric knowledge about those events. We present Q2E: a Query-to-Event decomposition method for zero-shot multilingual text-to-video retrieval, adaptable across datasets, domains, LLMs, or VLMs. Our approach demonstrates that we can enhance the understanding of otherwise overly simplified human queries by decomposing the query using the knowledge embedded in LLMs and VLMs. We additionally show how to apply our approach to both visual and speech-based inputs. To combine this varied multimodal knowledge, we adopt entropy-based fusion scoring for zero-shot fusion. Through evaluations on two diverse datasets and multiple retrieval metrics, we demonstrate that Q2E outperforms several state-of-the-art baselines. Our evaluation also shows that integrating audio information can significantly improve text-to-video retrieval. We have released code and data for future research.

ToxSyn-PT: A Large-Scale Synthetic Dataset for Hate Speech Detection in Portuguese

We present ToxSyn-PT, the first large-scale Portuguese corpus that enables fine-grained hate-speech classification across nine legally protected minority groups. The dataset contains 53,274 synthetic sentences equally distributed between minorities groups and toxicity labels. ToxSyn-PT is created through a novel four-stage pipeline: (1) a compact, manually curated seed; (2) few-shot expansion with an instruction-tuned LLM; (3) paraphrase-based augmentation; and (4) enrichment, plus additional neutral texts to curb overfitting to group-specific cues. The resulting corpus is class-balanced, stylistically diverse, and free from the social-media domain that dominate existing Portuguese datasets. Despite domain differences with traditional benchmarks, experiments on both binary and multi-label classification on the corpus yields strong results across five public Portuguese hate-speech datasets, demonstrating robust generalization even across domain boundaries. The dataset is publicly released to advance research on synthetic data and hate-speech detection in low-resource settings.