Speech_Recognition
-
Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition
2026-08-11 12:02:55Gaopeng Xu, Zhenyu Wang, Zheng Xue, Yinfeng Xia, Haitao YaoAbstract
The signal ambiguity of whispered speech drives ASR systems toward two opposing failure modes: failing to capture whispered speech or hallucinatory transcription of noise. This paper introduces the Whisper-Aware LLM, a framework that teaches an Audio-LLM to perceive and react to this uncertainty. Our model develops an intrinsic self-awareness by learning to quantify the physical deficiencies of acoustic signals through targeted self-supervised tasks. This learned uncertainty is then operationalized via a novel Confidence-Fused Decoding mechanism, which provides both high-level instructions and frame-level attention modulation to the LLM decoder. Our experiments confirm the effectiveness of this approach. The model sets a new state-of-the-art on whispered speech with a 17% relative CER reduction on AISHELL6-Whisper. At the same time, it directly addresses the reliability trade-off, with hallucination rates dropping from over 25% to 4.5%.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10836
PDF
-
Edge Phoneme Recognition for Children's Speech through Age-Aware Training
2026-08-10 20:20:56Matthew Arboleda, Ryan Arboleda, Sophie Haak, Sam Hjelmeset, Andrew Franck, Bingrui Yang, Jose Bustamante Ortiz, Yuanrong Shen, Joel WalshAbstract
Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's speech. During a phoneme detection competition, we found that training a lightweight model to predict the age of the learner, as well as the phoneme sequence, enabled a 94M-parameter model to outperform WavLM Large models (317M) on the target DrivenData distribution, and fall within approximately 0.04 CER of competition ensembles with 90 times the parameters. This has enabled the creation of PhonemeTrainer, an application that can run on most modern cellular phones. This will ultimately enable better Automated Speech Recognition (ASR) and pronunciation helper apps for children's speech, with the privacy and compliance benefits that come with edge processing.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10206
PDF
-
VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference
2026-08-09 08:17:18Wenxu Jia, Dongjie Fu, Xize Cheng, Fangming Feng, Linjun Li, Wenshi Chen, Yingming Li, Zhou Zhao, Tao JinAbstract
Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks. Despite this progress, their long-context inference remains severely bottlenecked by prohibitive KV cache memory demands. Existing text-centric compression methods struggle here, often disrupting speech continuity or discarding crucial semantic cues. To address this, we propose VoxZip, a train-free, two-stage semantic-anchored KV cache compression framework. The first stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temporally align, compress, and fuse audio tokens, significantly reducing the initial KV cache while elevating token information density. To further improve the compression ratio, the second stage employs a dynamic filtering strategy based on temporally decayed accumulated attention to evict non-essential tokens while mitigating early-token bias. Comprehensive evaluations on Qwen3-Omni across six diverse audio benchmarks demonstrate the superiority of our approach. VoxZip excels in long-audio reasoning and consistently maintains high-fidelity perception on short-form tasks. Notably, it sustains over 90\% of the uncompressed baseline performance even under an aggressive 20x KV cache compression in long-context scenarios. Furthermore, at a 4x compression ratio, VoxZip yields a 1.9x increase in inference throughput alongside a 3.3x reduction in peak memory overhead. Code and models will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08569
PDF
-
From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios
2026-08-09 06:11:38Thai-Binh Nguyen, Zhaolin Li, Jan Niehues, Alexander WaibelAbstract
Humans have the remarkable ability to engage in spontaneous informal conversations and selectively attend to individual speakers while filtering out competing speech from nearby conversations. This "cocktail party" scenario still presents severe challenges to speech recognition systems. The CHiME-9 MCoRec task provides a testbed where systems must recognize groups of speakers and transcribe each of their conversations from audio-visual input. In this work, we analyze a diverse set of systems, representing different design directions for addressing the cocktail-party scenario, where the best system achieves up to 57% relative error reduction. We identify three main strategies: (1) explicit or implicit audio-visual target speech separation, (2) improved audio-visual speech recognition for each target speaker, and (3) the use of large language models to group speakers into conversations and enhance conversational consistency. Our analysis shows that these directions address complementary failure modes of the cocktail-party problem, and that high speech overlap alone does not explain performance differences, challenging the common assumption that overlap is the primary source of difficulty in cocktail-party recognition.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08510
PDF
-
Scaling Audio Models Efficiently: A Joint Study of Compute Constraints and Optimization Behavior
2026-08-09 05:43:05Vyom Agarwal, Mokshda Gangrade, Siddharth Pal, Jerry WuAbstract
In this paper, we investigate the tradeoffs between compute allocation and model performance for two speech processing tasks: Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER). We propose a unified framework that analyzes three fundamental compute dimensions: model size ($x_N$), input length ($x_T$), and representation resolution ($x_V$). Motivated by recent advances in compute optimal scaling for multimodal models, we systematically vary these dimensions to examine their influence on task performance under fixed computational budgets. Our study provides insights into how compute resources can be optimally distributed across model capacity, temporal context, and representational granularity, offering practical guidelines for the design of efficient speech models. Through experiments on LibriSpeech and CREMA-D datasets, we demonstrate non-linear scaling behavior and identify optimal operating points. Our results show that (1) increasing model size yields diminishing returns: scaling Tiny (39M) to Small (244M) reduces WER by 8.22%, whereas Small to Medium (769M) reduces WER by only 2.35%; (2) an optimal audio duration of approximately 4 seconds exists for SER; and (3) reducing encoder token resolution provides an effective mechanism for lowering inference cost, Large-v3 (1540M) with 750 frames requires 2572 GFLOPS whereas with 1500 frames requires 5228 GFLOPS, with less than 3% relative increase in WER. Additionally, LoRA-based adaptation enables efficient finetuning with minimal performance degradation.
Abstract (translated)
URL
https://arxiv.org/abs/2606.22790
PDF
-
Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
2026-08-07 16:39:51Shengyuan Ye, Yixin Zhang, Han Liang, Liekang Zeng, Jiangsu Du, Mu YuanAbstract
\texttt{Homebot} is a locally deployable AI agent for conversational household assistance and automation. It accepts voice and instant-messaging requests through a shared runtime that combines language-model responses with registered tools and task-specific skills. The design separates common request processing from session ownership: messaging history remains scoped to a channel and chat, whereas voice interaction is bounded by wake-word activation. For hands-free use, \texttt{Homebot} combines local wake-word detection, streaming speech recognition and synthesis, and an explicit dialogue-state protocol for ending, following up, or continuing a conversation. Clear channel, tool, and skill contracts support practical customization for household use.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02254
PDF
-
Decolonizing Linguistic Policies in Automated Speech Recognition: A Framework for Cross-Culturally Competent Speech AI
2026-08-06 15:10:29Jay L. Cunningham, Mark Atta Mensah, Richard Martinez, Joao Vieira da Silva Neto, Efi DawoduAbstract
This paper focuses on automatic speech recognition (ASR) and ASR-mediated voice interfaces that shape access to public services, healthcare, and education. We argue that persistent failures for low-resource, Indigenous, and non-standard language varieties are not only technical errors, but also implicit linguistic policies that reproduce colonial language hierarchies. Drawing on linguistic capital, raciolinguistic ideology, language policy research, and decolonial computing, we show how data, metrics, and model priors determine whose voices become machine-legible. We introduce the Three Harms (3M) taxonomy---Misrecognition, Misalignment, and Mistrust---and a seven-layer situatedness model for linguistic diversity in ASR and ASR-mediated voice interfaces. We then propose a participatory framework and minimum audit protocol for culturally competent ASR, positioning affected communities as co-designers, evaluators, and governance partners.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06141
PDF
-
How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs
2026-08-06 08:45:33Christian Huber, Alexander WaibelAbstract
Recognizing new and rare words - named entities, acronyms, domain specific special words, and other items scarce in training data - remains a key challenge for automatic speech recognition (ASR). We compare two strategies for this: context biasing methods, where an ASR model is extended such that during inference a word list can be supplied, and speech large language models (LLMs) prompted with context directly. We evaluate two context biasing methods based on Whisper against three speech LLMs across read and non-read speech, reporting biased, unbiased, and overall word error rate (WER). The context biasing methods cut biased WER by up to 88% relative while leaving other words largely unaffected. Speech LLMs excel on read speech but generalize less well to non-read speech, and prove sensitive to distractor count and prompt word order. We characterize the resulting trade-offs to guide method selection.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05759
PDF
-
Vorch-Human: Unified Multi-Task Human-Centric Generation via Long-Horizon Continuation
2026-08-06 08:22:02Yang Ding, Haoran Yu, Xin Ma, Yulei Lu, Menglin Han, Yaole Wang, Siqian Yang, Gang Yue, Kaihao Zhang, Yaohui Wang, Lin MaAbstract
Human-centric audio-visual generation spans several closely related tasks: animating a person from driving speech, jointly generating speech and video from a voice reference, and synthesizing a scene from paired appearance and voice references. Existing systems commonly solve these tasks with separate models, even though they share the same target modalities and differ mainly in which observations are provided as conditions. We present Vorch-Human, a unified human-centric generation framework built on a dual-stream audio-video diffusion transformer. Vorch-Human augments the conventional noisy audio/noisy video interface with clean condition-audio and condition-video token groups. Per-token task embeddings, temporal position types, condition masks, and a shared multimodal prompt encoder allow driving speech, timbre examples, first frames, and subject images to be expressed within one model. To supply the supervision required by this interface, we develop a two-level data pipeline. Level 1 analyzes each clip with speech recognition, vocal separation, face detection and tracking, active-speaker and synchronization models, audio/visual speaker clustering, and multimodal caption correction; it produces subject-indexed speech, appearance, and timbre annotations. Level 2 links the same person across clips from a common source video and mines identity- and outfit-consistent reference images after face, body, quality, pose, and vision-language verification. Finally, we adapt Vorch-Human to long-form audio-driven generation by training with clean latent prefixes and using the same frozen-prefix recurrence at inference. Each segment contributes only its newly generated suffix, reducing boundary discontinuity and long-horizon identity drift. Experiments on short and five-minute generation demonstrate strong identity preservation, audio-visual synchronization, and temporal stability.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26117
PDF
-
Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study
2026-08-03 08:14:26Darwin Jelestin Muthu, Navya Gupta, Wei Lin Tay, Zhengchen Zhang, Daniel Wang Zhengkui, Rong TongAbstract
Automatic speech recognition (ASR) performance degrades sharply on dysarthric speech, yet how disordered articulation reshapes a model's internal representations is underexplored. We present a layer-wise probing analysis of a transformer ASR encoder on Mandarin dysarthric speech under three transcript-matched conditions: original dysarthric speech, speaker conditioned zero-shot TTS resynthesis, and unconditioned TTS. The probes reveal a task-dependent hierarchy: phoneme boundary information stays weak for dysarthric speech at every layer, phoneme identity becomes recoverable toward the upper layers, and recognition difficulty is encoded in the deepest layers. Tone-sensitive evaluation shows Mandarin lexical tone is a persistent error source. Cross-condition similarity divergence grows with depth, indicating that disordered speech affects high-level representations more than low-level acoustic features. Guided by these findings, single-layer LoRA at layer 7 and adaptation on subset layers 5-8 achieve performance within 3.5% and 2.48% relative margins of full encoder adaptation, respectively, while upper-layer adaptation is less effective for dysarthric speech. These findings link representation analysis to parameter-efficient fine-tuning and motivate layer-aware adaptation for low-resource Mandarin dysarthric ASR.
Abstract (translated)
URL
https://arxiv.org/abs/2608.01865
PDF
-
SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces
2026-08-01 18:03:37Ruidong Zhang, Jiacheng Liu, Fran\c{c}ois Guimbreti\`ere, Cheng ZhangAbstract
Wearable silent speech interfaces (SSIs) are limited to small, closed vocabularies. Approaches achieving larger vocabularies require obtrusive hardware such as facial electrodes. We present SoniSpeech, the first large-scale, open-vocabulary, trimodal dataset for wearable SSI using acoustic-sensing eyewear. It contains 34 hours across 18,000 utterances with three synchronized modalities: ultrasound echo profiles, voiced audio, and frontal video, in both voiced and silent modes. The corpus draws from the SODA dialogue dataset, providing contemporary conversational English with 5,356 unique words and full phoneme coverage. A CTC-based ResNet-34 baseline achieves 26.3% word error rate (WER) on open-vocabulary silent speech recognition, the first benchmark for this task. Dataset is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.00803
PDF
-
Normal-Anchored First-Order Model-Agnostic Meta-Learning based Whisper Fine-Tuning for Enhancing Fairness of Cleft Lip and Palate Speech Recognition
2026-07-31 18:08:53Susmita Bhattacharjee, Jagabandhu Mishra, H. S. Shekhawat, Ravi Jasuja, S. R. Mahadeva PrasannaAbstract
Automatic speech recognition (ASR) for cleft lip and palate (CLP) speech is difficult because acoustic and articulatory patterns vary across severity levels. This variability reduces the performance of pretrained ASR systems, and conventional fine-tuning may not generalize well under low-resource, heterogeneous CLP conditions. This work proposes Normal-Anchored First-Order Model-Agnostic Meta-Learning (NA-FOMAML) for adapting Whisper to CLP speech. The method uses a first-order bilevel meta-learning framework in which normal speech is used in the inner loop as a stable support condition, while CLP severity groups are used in the outer loop to improve post-adaptation robustness. This design aims to reduce the performance gap between normal and pathological speech. Experiments are conducted on the NMCPC and AIISH datasets using four normal-anchored training configurations. Frozen encoder, full encoder, and selected Whisper encoder-layer tuning strategies are evaluated, including layers 0--5, 4--11, 6--11, and 8--11, with decoder and projection-head adaptation. Results show that outer-loop training with only normal speech is insufficient. For NMCPC, full encoder tuning with Normal to Normal+Mild+Moderate gives WERs of 4.40%, 5.53%, 16.14%, and 52.07% for normal, mild, moderate, and severe speech. For AIISH, full encoder tuning with Normal to Normal+Mild+Moderate+Severe gives WERs of 2.48%, 19.66%, 14.05%, and 57.50%. A transcription-based phoneme-category analysis shows that severe CLP speech has high error rates across fricatives, affricates, nasals, liquids, plosives, and vowels. Overall, NA-FOMAML improves cross-severity robustness, but severe speech still requires severity-aware sampling, phoneme-aware loss functions, and augmentation targeting pressure consonant and resonance-related distortions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.00186
PDF
-
ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition
2026-07-31 10:50:14Qingjian Lin, Yuxin Li, Haoyang Zhang, Jun Chen, Yechang Huang, Feng Tian, Xie Li, Xiangyu Tony Zhang, Daijiao Liu, Yuxin Zhang, Jinglan Gong, Bo Zhao, Fei Tian, Xuerui Yang, Gang Yu, Xiangyu Zhang, Daxin JiangAbstract
Audio-encoder-LLM-decoder architectures have become the dominant paradigm for modern automatic speech recognition (ASR), improving transcription quality through large-scale language modeling. However, the cost of autoregressive decoding scales with decoder size, creating a fundamental trade-off between recognition quality and serving latency. We argue this trade-off is not inherent: unlike open-ended text generation, ASR outputs are strongly anchored to the input speech signal, providing a natural inductive bias toward high-parallelism decoding. Building on this, we introduce ParaASR, an ASR system that leverages Multi-Token Prediction (MTP) to let a 4B LLM decoder emit multiple tokens per forward step. Starting from a publicly available audio-language foundation, the model first establishes a robust autoregressive recognizer and then aligns five future-token branches through a staged optimization recipe. At inference, it proposes a six-token continuation per step and admits only the verified prefix into the transcript, preserving the safety of standard autoregressive decoding. The average accepted length reaches 5.0 out of 6 proposed tokens, confirming that the deterministic structure of speech makes ASR an especially natural setting for multi-token decoding. ParaASR further retains a native 32K-context window and transcribes up to 30 minutes of audio in a single pass. Across diverse benchmarks, it attains average error rates of 2.97%, 3.68%, and 3.70% on Chinese, English, and long-form evaluations, respectively, while reaching a real-time factor (RTF) as low as 0.0053. These results show that decoder scaling, low-latency inference, and long-context transcription need not be competing goals when future-token proposals are anchored by the acoustic signal and guarded by autoregressive verification.
Abstract (translated)
URL
https://arxiv.org/abs/2607.29279
PDF
-
DoubleHelix: Structured Cross-Modal Fusion for Audio-Visual Speech Recognition with LLMs
2026-07-31 07:40:59Ziwei Cheng, Zhenhua Tan, Zhuomin ZhuAbstract
Audio-visual speech recognition (AVSR) relies on effective fusion of audio and visual modalities, yet existing approaches treat cross-modal interaction as a single-step operation without structured iterative refinement. We present DoubleHelix, a multimodal fusion framework that reformulates fusion as an iterative cross-modal interaction process with adaptive degradation-aware enhancement. The framework comprises three components including ReverseParallelHelix for multi-turn structured interaction with learned alignment constraints, QualitySensor for learning degradation-aware gating signals, and HelixReplication for consistency-guided conditional feature enhancement. Experiments on LRS3 demonstrate that DoubleHelix achieves 0.68% WER on clean audio, outperforming previous best results by 5.6% relative improvement under matched backbone settings. Comprehensive ablation studies validate each component contribution, including targeted analysis of design choices such as asymmetric pathway weighting. The framework shows improved robustness under evaluated babble-noise conditions, achieving 11.6% WER at SNR -5dB.
Abstract (translated)
URL
https://arxiv.org/abs/2607.29112
PDF
-
Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition
2026-07-30 04:56:46Matthew Kit Khinn Teng, Haibo Zhang, Takeshi SaitohAbstract
Phoneme-centric visual speech recognition reconstructs sentences from intermediate phoneme predictions, making overall recognition performance highly dependent on the robustness of the phoneme-to-text reconstruction model. Existing reconstruction approaches are commonly trained on clean phoneme sequences or synthetically corrupted inputs, leading to a mismatch between training conditions and the realistic phoneme prediction errors encountered during inference. To address this limitation, this paper proposes progressive error curriculum training (PECT). This curriculum learning framework progressively adapts a No Language Left Behind (NLLB)-based phoneme-to-text reconstruction model using synthetic phoneme perturbations, multi-domain pseudo-labels, and target-domain pseudo-labels generated by a visual speech recognizer. By gradually exposing the reconstruction model to increasingly realistic phoneme prediction errors, the proposed framework improves robustness while preserving sentence-reconstruction accuracy. Experiments on the LRS2 and LRS3 benchmarks demonstrate that PECT consistently improves reconstruction performance across multiple phoneme-based visual speech recognition frontends, including visual automatic speech recognition (V-ASR), point visual automatic speech recognition (PV-ASR), and head-pose-aware visual speech recognition (HP-VSR) variants. In particular, PECT reduces the word error rate (WER) of HP-VSR-FiLMFuse (L4) from 23.3% to 22.2% on LRS2 and reduces the WER of HP-VSR-ResFiLM from 30.3% to 29.7% on LRS3. Comprehensive ablation studies and qualitative analyses further demonstrate the effectiveness of progressively adapting the reconstruction model to realistic phoneme prediction errors. These results show that PECT provides an effective and generalizable curriculum learning strategy for phoneme-to-text reconstruction in phoneme-centric visual speech recognition.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20839
PDF
-
Voice Memory for Agentic Speech Recognition
2026-07-29 02:42:56Chao-Han Huck Yang, Zih-Ching Chen, Piotr Zelasko, Zhehuai Chen, Jagadeesh Balam, Boris GinsburgAbstract
We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain this http URL and decides per utterance whether to act on the hypothesis or abstain and keep the 1-best. Asynchronously, a score-gated optimizer revises that file through bounded edits, accepting an edit only when it strictly improves a held-out score. Extended from classical ASR-LM framework, we refer this split the listener-thinker architecture; the two roles are coupled only through the memory, so no weights change and the learned skill stays auditable and portable. Restraint turns out to be the operative skill this loop discovers: unconstrained generative error correction (GER) over-corrects, breaking correct tokens on up to 64% of its edits on financial news, and Voice Memory, reduces this rate to 35%. Across ten HyPoradise domains with an open corrector, Voice Memory, lowers weighted word error rate from 8.36% to 7.52% (7.47% with three added in-context examples) without regressing any dataset below its 1-best baseline; gains concentrate where recoverable headroom is largest, including air-travel commands (8.40% to 3.40%) and noisy far-field speech (CHiME-4, 12.69% to 10.46%). The memory transfers across corrector families and adds zero parameters to the inference path. A demo and example code are provided for future studies.
Abstract (translated)
URL
https://arxiv.org/abs/2607.26410
PDF
-
SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies
2026-07-28 13:43:04Mohamed Nabih Ali, Daniele Falavigna, Alessio BruttiAbstract
Federated learning (FL) enables privacy-preserving training of automatic speech recognition (ASR) systems across distributed data sources, yet its application to large-scale speech language models (SpeechLLMs) remains unexplored. This paper presents the first systematic study of federated training for SpeechLLM-based end-to-end ASR systems. We design a communication-efficient federated optimization strategy tailored to the unique challenges of SpeechLLM architectures, addressing high-dimensional parameter spaces, gradient communication overhead, and computational constraints in distributed settings. Through extensive empirical evaluation on monolingual ASR tasks in English and Italian, we demonstrate the effectiveness and stability of our federated approach compared to centralized training baselines across diverse acoustic conditions and speaking styles. Additionally, we conduct a comprehensive ablation study analyzing the impact of different speech encoder architectures on monolingual English ASR performance within the federated framework, providing insights into optimal model configurations for decentralized training. Our results achieve competitive word error rates while reducing communication costs, establishing practical foundations for federated SpeechLLM deployment in real-world multilingual scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25716
PDF
-
Analyzing the Importance of Blank for CTC-Based Knowledge Distillation
2026-07-27 08:27:09Benedikt Hilmes, Nick Rossenbach, Ralf Schl\"uterAbstract
With the rise of large pre-trained foundation models for automatic speech recognition new challenges appear. While the performance of these models is good, runtime and cost of inference increases. One approach to make use of their strength while retaining efficiency is to distill their knowledge to smaller models during training. In this work, we explore different CTC-based distillation variants, focusing on blank token handling. We show that common approaches like blank elimination do not always work off the shelf. We explore new blank selection patterns as a potential sweet spot between standard knowledge distillation and blank elimination mechanisms. Through the introduction of a symmetric selection method, we are able to remove the CTC loss during knowledge distillation with minimal to no performance degradation. With this, we make the training independent from target labels, potentially allowing for distillation on untranscribed audio data.
Abstract (translated)
URL
https://arxiv.org/abs/2506.01503
PDF
-
MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition
2026-07-27 05:55:50Sangmin Lee, Woojin Chung, Woongjib Choi, Hong-Goo KangAbstract
Massively multilingual automatic speech recognition (ASR) models covering hundreds of languages must maintain robust performance across diverse linguistic and acoustic conditions. However, these models often encounter the curse of multilinguality, where model capacity is diluted across languages. To address this challenge, we propose Mixture of Language Group Experts (MoLGE), built upon speech self-supervised models (S3Ms). MoLGE assigns dedicated expert modules to clusters of similar languages, reducing the number of required submodules compared to conventional language-specific Mixture-of-Experts (MoE) schemes. It further integrates a hierarchical Low-Rank Adaptation (LoRA) strategy into the disentangled acoustic and linguistic components of the S3M architecture, enabling efficient modeling of language-specific characteristics while maintaining parameter efficiency. Further, we investigate the impact of language grouping strategies based on both linguistic and data-driven criteria on overall performance, providing an interpretable perspective on how language structure influences scalability in multilingual speech systems. In experiments, we evaluate MoLGE on a multilingual benchmark encompassing 495 languages. Results demonstrate that MoLGE consistently outperforms dense multilingual baselines with a minimal increase in trainable parameters. Notably, these language grouping strategies yield substantial improvements for both phonetic and orthographic aspects of ASR modeling. Our findings suggest that structured language specialization provides an effective pathway for massively scaling language coverage of multilingual ASR.
Abstract (translated)
URL
https://arxiv.org/abs/2607.24030
PDF
-
Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance
2026-07-26 19:24:00Denglin Jiang, Haoran Zhou, Anshul Wadhawan, Brendan Fahy, Vinay Ramesh, David Weisberg, Dmitriy Derkachevskiy, Helen Sheehan, Srivas Prasad, Michele FranceschiniAbstract
We introduce Earnings25, a finance-domain benchmark for evaluating automatic speech recognition (ASR) on English-language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-language S&P 500 earnings calls from Q4 2025, and (ii) testset-segmented, a 46-hour industry-balanced set of 290 segments sampled from English-language U.S. earnings calls in 2025. The benchmark provides aligned transcripts and structured metadata, including speaker roles, industry labels, and call structure, enabling speaker- and industry-aware evaluation beyond aggregate word error rate (WER). We report reproducible baselines for Whisper and Parakeet-TDT using standardized scoring.
Abstract (translated)
URL
https://arxiv.org/abs/2607.23813
PDF
