Sink or SWIM: Tackling Real-Time ASR at Scale

Real-time automatic speech recognition systems are increasingly integrated into interactive applications, from voice assistants to live transcription services. However, scaling these systems to support multiple concurrent clients while maintaining low latency and high accuracy remains a major challenge. In this work, we present SWIM, a novel real-time ASR system built on top of OpenAI's Whisper model that enables true model-level parallelization for scalable, multilingual transcription. SWIM supports multiple concurrent audio streams without modifying the underlying model. It introduces a buffer merging strategy that maintains transcription fidelity while ensuring efficient resource usage. We evaluate SWIM in multi-client settings -- scaling up to 20 concurrent users -- and show that it delivers accurate real-time transcriptions in English, Italian, and Spanish, while maintaining low latency and high throughput. While Whisper-Streaming achieves a word error rate of approximately 8.2% with an average delay of approximately 3.4 s in a single-client, English-only setting, SWIM extends this capability to multilingual, multi-client environments. It maintains comparable accuracy with significantly lower delay -- around 2.4 s with 5 clients -- and continues to scale effectively up to 20 concurrent clients without degrading transcription quality and increasing overall throughput. Our approach advances scalable ASR by improving robustness and efficiency in dynamic, multi-user environments.

Deaf and Hard of Hearing Access to Intelligent Personal Assistants: Comparison of Voice-Based Options with an LLM-Powered Touch Interface

We investigate intelligent personal assistants (IPAs) accessibility for deaf and hard of hearing (DHH) people who can use their voice in everyday communication. The inability of IPAs to understand diverse accents including deaf speech renders them largely inaccessible to non-signing and speaking DHH individuals. Using an Echo Show, we compare the usability of natural language input via spoken English; with Alexa's automatic speech recognition and a Wizard-of-Oz setting with a trained facilitator re-speaking commands against that of a large language model (LLM)-assisted touch interface in a mixed-methods study. The touch method was navigated through an LLM-powered "task prompter," which integrated the user's history and smart environment to suggest contextually-appropriate commands. Quantitative results showed no significant differences across both spoken English conditions vs LLM-assisted touch. Qualitative results showed variability in opinions on the usability of each method. Ultimately, it will be necessary to have robust deaf-accented speech recognized natively by IPAs.

A Baseline Multimodal Approach to Emotion Recognition in Conversations

We present a lightweight multimodal baseline for emotion recognition in conversations using the SemEval-2024 Task 3 dataset built from the sitcom Friends. The goal of this report is not to propose a novel state-of-the-art method, but to document an accessible reference implementation that combines (i) a transformer-based text classifier and (ii) a self-supervised speech representation model, with a simple late-fusion ensemble. We report the baseline setup and empirical results obtained under a limited training protocol, highlighting when multimodal fusion improves over unimodal models. This preprint is provided for transparency and to support future, more rigorous comparisons.

SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models

Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulation remains poorly understood. We study a realistic and underexplored threat model: untargeted, audio-only adversarial attacks on trimodal audio-video-language models. We analyze six complementary attack objectives that target different stages of multimodal processing, including audio encoder representations, cross-modal attention, hidden states, and output likelihoods. Across three state-of-the-art models and multiple benchmarks, we show that audio-only perturbations can induce severe multimodal failures, achieving up to 96% attack success rate. We further show that attacks can be successful at low perceptual distortions (LPIPS <= 0.08, SI-SNR >= 0) and benefit more from extended optimization than increased data scale. Transferability across models and encoders remains limited, while speech recognition systems such as Whisper primarily respond to perturbation magnitude, achieving >97% attack success under severe distortion. These results expose a previously overlooked single-modality attack surface in multimodal systems and motivate defenses that enforce cross-modal consistency.

Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception

We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult external audio perception. Our work is motivated by a crucial yet counterintuitive finding: naively fine-tuning an omni-model on both speech recognition and external sound understanding tasks often degrades performance, as the model can be easily misled by noisy hypotheses. To address this, our framework, Speech-Hands, recasts the problem as an explicit self-reflection decision. This learnable reflection primitive proves effective in preventing the model from being derailed by flawed external candidates. We show that this agentic action mechanism generalizes naturally from speech recognition to complex, multiple-choice audio reasoning. Across the OpenASR leaderboard, Speech-Hands consistently outperforms strong baselines by 12.1% WER on seven benchmarks. The model also achieves 77.37% accuracy and high F1 on audio QA decisions, showing robust generalization and reliability across diverse audio question answering datasets. By unifying perception and decision-making, our work offers a practical path toward more reliable and resilient audio intelligence.

Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers

Traditional speech systems typically rely on separate, task-specific models for text-to-speech (TTS), automatic speech recognition (ASR), and voice conversion (VC), resulting in fragmented pipelines that limit scalability, efficiency, and cross-task generalization. In this paper, we present General-Purpose Audio (GPA), a unified audio foundation model that integrates multiple core speech tasks within a single large language model (LLM) architecture. GPA operates on a shared discrete audio token space and supports instruction-driven task induction, enabling a single autoregressive model to flexibly perform TTS, ASR, and VC without architectural modifications. This unified design combines a fully autoregressive formulation over discrete speech tokens, joint multi-task training across speech domains, and a scalable inference pipeline that achieves high concurrency and throughput. The resulting model family supports efficient multi-scale deployment, including a lightweight 0.3B-parameter variant optimized for edge and resource-constrained environments. Together, these design choices demonstrate that a unified autoregressive architecture can achieve competitive performance across diverse speech tasks while remaining viable for low-latency, practical deployment.

Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding

Code understanding is a foundational capability in software engineering tools and developer workflows. However, most existing systems are designed for English-speaking users interacting via keyboards, which limits accessibility in multilingual and voice-first settings, particularly in regions like India. Voice-based interfaces offer a more inclusive modality, but spoken queries involving code present unique challenges due to the presence of non-standard English usage, domain-specific vocabulary, and custom identifiers such as variable and function names, often combined with code-mixed expressions. In this work, we develop a multilingual speech-driven framework for code understanding that accepts spoken queries in a user native language, transcribes them using Automatic Speech Recognition (ASR), applies code-aware ASR output refinement using Large Language Models (LLMs), and interfaces with code models to perform tasks such as code question answering and code retrieval through benchmarks such as CodeSearchNet, CoRNStack, and CodeQA. Focusing on four widely spoken Indic languages and English, we systematically characterize how transcription errors impact downstream task performance. We also identified key failure modes in ASR for code and demonstrated that LLM-guided refinement significantly improves performance across both transcription and code understanding stages. Our findings underscore the need for code-sensitive adaptations in speech interfaces and offer a practical solution for building robust, multilingual voice-driven programming tools.

PRiSM: Benchmarking Phone Realization in Speech Models

Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis. Despite prolonged efforts in developing PR systems, current evaluations only measure surface-level transcription accuracy. We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception through intrinsic and extrinsic evaluation of PR systems. PRiSM standardizes transcription-based evaluation and assesses downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. We find that diverse language exposure during training is key to PR performance, encoder-CTC models are the most stable, and specialized PR models still outperform Large Audio Language Models. PRiSM releases code, recipes, and datasets to move the field toward multilingual speech models with robust phonetic ability: https://github.com/changelinglab/prism.

CTC-DID: CTC-Based Arabic dialect identification for streaming applications

This paper proposes a Dialect Identification (DID) approach inspired by the Connectionist Temporal Classification (CTC) loss function as used in Automatic Speech Recognition (ASR). CTC-DID frames the dialect identification task as a limited-vocabulary ASR system, where dialect tags are treated as a sequence of labels for a given utterance. For training, the repetition of dialect tags in transcriptions is estimated either using a proposed Language-Agnostic Heuristic (LAH) approach or a pre-trained ASR model. The method is evaluated on the low-resource Arabic Dialect Identification (ADI) task, with experimental results demonstrating that an SSL-based CTC-DID model, trained on a limited dataset, outperforms both fine-tuned Whisper and ECAPA-TDNN models. Notably, CTC-DID also surpasses these models in zero-shot evaluation on the Casablanca dataset. The proposed approach is found to be more robust to shorter utterances and is shown to be easily adaptable for streaming, real-time applications, with minimal performance degradation.

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem

Speech processing for low-resource dialects remains a fundamental challenge in developing inclusive and robust speech technologies. Despite its linguistic significance and large speaker population, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models. In this work, we present WenetSpeech-Wu, the first large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect, comprising approximately 8,000 hours of diverse speech data. Building upon this dataset, we introduce WenetSpeech-Wu-Bench, the first standardized and publicly accessible benchmark for systematic evaluation of Wu dialect speech processing, covering automatic speech recognition (ASR), Wu-to-Mandarin translation, speaker attribute prediction, speech emotion recognition, text-to-speech (TTS) synthesis, and instruction-following TTS (instruct TTS). Furthermore, we release a suite of strong open-source models trained on WenetSpeech-Wu, establishing competitive performance across multiple tasks and empirically validating the effectiveness of the proposed dataset. Together, these contributions lay the foundation for a comprehensive Wu dialect speech processing ecosystem, and we open-source proposed datasets, benchmarks, and models to support future research on dialectal speech intelligence.