Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets

The advancement of automatic speech recognition (ASR) has been largely enhanced by extensive datasets in high-resource languages, while languages such as Hungarian remain underrepresented due to limited spontaneous and conversational corpora. To address this gap, we introduce two new datasets -- BEA-Large and BEA-Dialogue -- constructed from the previously unprocessed portions of the Hungarian speech corpus named BEA. BEA-Large extends BEA-Base with 255 hours of spontaneous speech from 433 speakers, enriched with detailed segment-level metadata. BEA-Dialogue, comprising 85 hours of spontaneous conversations, is a Hungarian speech corpus featuring natural dialogues partitioned into speaker-independent subsets, supporting research in conversational ASR and speaker diarization. We establish reproducible baselines on these datasets using publicly available ASR models, with the fine-tuned Fast Conformer model achieving word error rates as low as 14.18\% on spontaneous and 4.8\% on repeated speech. Diarization experiments yield diarization error rates between 13.05\% and 18.26\%, providing reference points for future improvements. The results highlight the persistent difficulty of conversational ASR, particularly due to disfluencies, overlaps, and informal speech patterns. By releasing these datasets and baselines, we aim to advance Hungarian speech technology and offer a methodological framework for developing spontaneous and conversational benchmarks in other languages.

Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition

Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as conference presentations. This challenge arises primarily due to constrained model context windows and the sparsity of relevant information within extensive contextual noise. To solve this, we propose the SAP$^{2}$ method, a novel framework that dynamically prunes and integrates relevant contextual keywords in two stages. Specifically, each stage leverages our proposed Speech-Driven Attention-based Pooling mechanism, enabling efficient compression of context embeddings while preserving speech-salient information. Experimental results demonstrate state-of-the-art performance of SAP$^{2}$ on the SlideSpeech and LibriSpeech datasets, achieving word error rates (WER) of 7.71% and 1.12%, respectively. On SlideSpeech, our method notably reduces biased keyword error rates (B-WER) by 41.1% compared to non-contextual baselines. SAP$^{2}$ also exhibits robust scalability, consistently maintaining performance under extensive contextual input conditions on both datasets.

Context-Aware Dynamic Chunking for Streaming Tibetan Speech Recognition

In this work, we propose a streaming speech recognition framework for Amdo Tibetan, built upon a hybrid CTC/Atten-tion architecture with a context-aware dynamic chunking mechanism. The proposed strategy adaptively adjusts chunk widths based on encoding states, enabling flexible receptive fields, cross-chunk information exchange, and robust adaptation to varying speaking rates, thereby alleviating the context truncation problem of fixed-chunk methods. To further capture the linguistic characteristics of Tibetan, we construct a lexicon grounded in its orthographic principles, providing linguistically motivated modeling units. During decoding, an external language model is integrated to enhance semantic consistency and improve recognition of long sentences. Experimental results show that the proposed framework achieves a word error rate (WER) of 6.23% on the test set, yielding a 48.15% relative improvement over the fixed-chunk baseline, while significantly reducing recognition latency and maintaining performance close to global decoding.

TTA: Transcribe, Translate and Alignment for Cross-lingual Speech Representation

Speech-LLM models have demonstrated great performance in multi-modal and multi-task speech understanding. A typical speech-LLM paradigm is integrating speech modality with a large language model (LLM). While the Whisper encoder was frequently adopted in previous studies for speech input, it shows limitations regarding input format, model scale, and semantic performance. To this end, we propose a lightweight TTA model specialized in speech semantics for more effective LLM integration. With large-scale training of 358k hours of speech data on multilingual speech recognition (ASR), speech translation (ST) and speech-text alignment tasks, TTA is capable of producing robust cross-lingual speech representations. Extensive evaluations across diverse benchmarks, including ASR/ST, speech retrieval, and ASR-LLM performance assessments, demonstrate TTA's superiority over Whisper. Furthermore, we rigorously validate the interplay between cross-lingual capabilities and ASR/ST performance. The model weights and training recipes of TTA will be released as part of an audio understanding toolkit Auden.

Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by architectures that restrict language support, making extension inaccessible to most--all while entangled with ethical concerns when pursued without community collaboration. To transcend these limitations, we introduce Omnilingual ASR, the first large-scale ASR system designed for extensibility. Omnilingual ASR enables communities to introduce unserved languages with only a handful of data samples. It scales self-supervised pre-training to 7B parameters to learn robust speech representations and introduces an encoder-decoder architecture designed for zero-shot generalization, leveraging a LLM-inspired decoder. This capability is grounded in a massive and diverse training corpus; by combining breadth of coverage with linguistic variety, the model learns representations robust enough to adapt to unseen languages. Incorporating public resources with community-sourced recordings gathered through compensated local partnerships, Omnilingual ASR expands coverage to over 1,600 languages, the largest such effort to date--including over 500 never before served by ASR. Automatic evaluations show substantial gains over prior systems, especially in low-resource conditions, and strong generalization. We release Omnilingual ASR as a family of models, from 300M variants for low-power devices to 7B for maximum accuracy. We reflect on the ethical considerations shaping this design and conclude by discussing its societal impact. In particular, we highlight how open-sourcing models and tools can lower barriers for researchers and communities, inviting new forms of participation. Open-source artifacts are available at https://github.com/facebookresearch/omnilingual-asr.

Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues

Explainable AI (XAI) for Speech Emotion Recognition (SER) is critical for building transparent, trustworthy models. Current saliency-based methods, adapted from vision, highlight spectrogram regions but fail to show whether these regions correspond to meaningful acoustic markers of emotion, limiting faithfulness and interpretability. We propose a framework that overcomes these limitations by quantifying the magnitudes of cues within salient regions. This clarifies "what" is highlighted and connects it to "why" it matters, linking saliency to expert-referenced acoustic cues of speech emotions. Experiments on benchmark SER datasets show that our approach improves explanation quality by explicitly linking salient regions to theory-driven speech emotions expert-referenced acoustics. Compared to standard saliency methods, it provides more understandable and plausible explanations of SER models, offering a foundational step towards trustworthy speech-based affective computing.

SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition

Spiking neural networks (SNNs) offer a promising path toward energy-efficient speech command recognition (SCR) by leveraging their event-driven processing paradigm. However, existing SNN-based SCR methods often struggle to capture rich temporal dependencies and contextual information from speech due to limited temporal modeling and binary spike-based representations. To address these challenges, we first introduce the multi-view spiking temporal-aware self-attention (MSTASA) module, which combines effective spiking temporal-aware attention with a multi-view learning framework to model complementary temporal dependencies in speech commands. Building on MSTASA, we further propose SpikCommander, a fully spike-driven transformer architecture that integrates MSTASA with a spiking contextual refinement channel MLP (SCR-MLP) to jointly enhance temporal context modeling and channel-wise feature integration. We evaluate our method on three benchmark datasets: the Spiking Heidelberg Dataset (SHD), the Spiking Speech Commands (SSC), and the Google Speech Commands V2 (GSC). Extensive experiments demonstrate that SpikCommander consistently outperforms state-of-the-art (SOTA) SNN approaches with fewer parameters under comparable time steps, highlighting its effectiveness and efficiency for robust speech command recognition.

Fusionista2.0: Efficiency Retrieval System for Large-Scale Datasets

The Video Browser Showdown (VBS) challenges systems to deliver accurate results under strict time constraints. To meet this demand, we present Fusionista2.0, a streamlined video retrieval system optimized for speed and usability. All core modules were re-engineered for efficiency: preprocessing now relies on ffmpeg for fast keyframe extraction, optical character recognition uses Vintern-1B-v3.5 for robust multilingual text recognition, and automatic speech recognition employs faster-whisper for real-time transcription. For question answering, lightweight vision-language models provide quick responses without the heavy cost of large models. Beyond these technical upgrades, Fusionista2.0 introduces a redesigned user interface with improved responsiveness, accessibility, and workflow efficiency, enabling even non-expert users to retrieve relevant content rapidly. Evaluations demonstrate that retrieval time was reduced by up to 75% while accuracy and user satisfaction both increased, confirming Fusionista2.0 as a competitive and user-friendly system for large-scale video search.

Spatial Blind Spot: Auditory Motion Perception Deficits in Audio LLMs

Large Audio-Language Models (LALMs) have recently shown impressive progress in speech recognition, audio captioning, and auditory question answering. Yet, whether these models can perceive spatial dynamics, particularly the motion of sound sources, remains unclear. In this work, we uncover a systematic motion perception deficit in current ALLMs. To investigate this issue, we introduce AMPBench, the first benchmark explicitly designed to evaluate auditory motion understanding. AMPBench introduces a controlled question-answering benchmark designed to evaluate whether Audio-Language Models (LALMs) can infer the direction and trajectory of moving sound sources from binaural audio. Comprehensive quantitative and qualitative analyses reveal that current models struggle to reliably recognize motion cues or distinguish directional patterns. The average accuracy remains below 50%, underscoring a fundamental limitation in auditory spatial reasoning. Our study highlights a fundamental gap between human and model auditory spatial reasoning, providing both a diagnostic tool and new insight for enhancing spatial cognition in future Audio-Language Models.

Distinguishing Repetition Disfluency from Morphological Reduplication in Bangla ASR Transcripts: A Novel Corpus and Benchmarking Analysis

Automatic Speech Recognition (ASR) transcripts, especially in low-resource languages like Bangla, contain a critical ambiguity: word-word repetitions can be either Repetition Disfluency (unintentional ASR error/hesitation) or Morphological Reduplication (a deliberate grammatical construct). Standard disfluency correction fails by erroneously deleting valid linguistic information. To solve this, we introduce the first publicly available, 20,000-row Bangla corpus, manually annotated to explicitly distinguish between these two phenomena in noisy ASR transcripts. We benchmark this novel resource using two paradigms: state-of-the-art multilingual Large Language Models (LLMs) and task-specific fine-tuning of encoder models. LLMs achieve competitive performance (up to 82.68\% accuracy) with few-shot prompting. However, fine-tuning proves superior, with the language-specific BanglaBERT model achieving the highest accuracy of 84.78\% and an F1 score of 0.677. This establishes a strong, linguistically-informed baseline and provides essential data for developing sophisticated, semantic-preserving text normalization systems for Bangla.