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.

Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic Speech Networks

Edge devices operate in constrained and varying resource settings, requiring dynamic architectures that can adapt to limitations of the available resources. To meet such demands, layer dropping ($\mathcal{LD}$) approach is typically used to transform static models into dynamic ones by skipping parts of the network along with reducing overall computational complexity. However, existing $\mathcal{LD}$ methods greatly impact the dynamic model's performance for low and high dropping cases, deteriorating the performance-computation trade-off. To this end, we propose a distillation-based layer dropping (DLD) framework that effectively combines the capabilities of knowledge distillation and $\mathcal{LD}$ in an end-to-end fashion, thereby achieving state-of-the-art performance for dynamic speech networks. Comprehensive experimentation utilizing well-known speech recognition methods, including conformer and WavLM, on three public benchmarks demonstrates the effectiveness of our framework, reducing the word error rate by $9.32\%$ and $2.25\%$ for high and no dropping cases with $33.3\%$ reduction in training time.

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.

SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper

Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a major challenge. While some approaches achieve strong performance when fine-tuned on specific domains, few systems generalize well across out-of-domain datasets. Our prior work, Diarization-Conditioned Whisper (DiCoW), leverages speaker diarization outputs as conditioning information and, with minimal fine-tuning, demonstrated strong multilingual and multi-domain performance. In this paper, we address a key limitation of DiCoW: ambiguity in Silence-Target-Non-target-Overlap (STNO) masks, where two or more fully overlapping speakers may have nearly identical conditioning despite differing transcriptions. We introduce SE-DiCoW (Self-Enrolled Diarization-Conditioned Whisper), which uses diarization output to locate an enrollment segment anywhere in the conversation where the target speaker is most active. This enrollment segment is used as fixed conditioning via cross-attention at each encoder layer. We further refine DiCoW with improved data segmentation, model initialization, and augmentation. Together, these advances yield substantial gains: SE-DiCoW reduces macro-averaged tcpWER by 52.4% relative to the original DiCoW on the EMMA MT-ASR benchmark.

Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries

Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a pretrained LLM via a lightweight connector. Prior work trains a separate connector per language, overlooking linguistic relatedness. We propose an efficient and novel connector-sharing strategy based on linguistic family membership, enabling one connector per family, and empirically validate its effectiveness across two multilingual LLMs and two real-world corpora spanning curated and crowd-sourced speech. Our results show that family-based connectors reduce parameter count while improving generalization across domains, offering a practical and scalable strategy for multilingual ASR deployment.

MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading

Lipreading, the technology of decoding spoken content from silent videos of lip movements, holds significant application value in fields such as public security. However, due to the subtle nature of articulatory gestures, existing lipreading methods often suffer from limited feature discriminability and poor generalization capabilities. To address these challenges, this paper delves into the purification of visual features from temporal, spatial, and channel dimensions. We propose a novel method named Multi-Attention Lipreading Network(MA-LipNet). The core of MA-LipNet lies in its sequential application of three dedicated attention modules. Firstly, a \textit{Channel Attention (CA)} module is employed to adaptively recalibrate channel-wise features, thereby mitigating interference from less informative channels. Subsequently, two spatio-temporal attention modules with distinct granularities-\textit{Joint Spatial-Temporal Attention (JSTA)} and \textit{Separate Spatial-Temporal Attention (SSTA)}-are leveraged to suppress the influence of irrelevant pixels and video frames. The JSTA module performs a coarse-grained filtering by computing a unified weight map across the spatio-temporal dimensions, while the SSTA module conducts a more fine-grained refinement by separately modeling temporal and spatial attentions. Extensive experiments conducted on the CMLR and GRID datasets demonstrate that MA-LipNet significantly reduces the Character Error Rate (CER) and Word Error Rate (WER), validating its effectiveness and superiority over several state-of-the-art methods. Our work highlights the importance of multi-dimensional feature refinement for robust visual speech recognition.

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.

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.

Efficient Rehearsal for Continual Learning in ASR via Singular Value Tuning

Continual Learning (CL) in Automatic Speech Recognition (ASR) suffers from catastrophic forgetting when adapting to new tasks, domains, or speakers. A common strategy to mitigate this is to store a subset of past data in memory for rehearsal. However, rehearsal-based methods face key limitations: storing data is often costly, infeasible with pre-trained models, or restricted by privacy regulations. Running existing rehearsal-based methods with smaller memory sizes to alleviate these issues usually leads to degraded performance. We propose a rehearsal-based CL method that remains effective even with minimal memory. It operates in two stages: first, fine-tuning on the new task; second, applying Singular Value Decomposition (SVD) to the changes in linear layers and, in a parameter-efficient manner, retraining only gating vectors on the singular values, which control to extent to which updates from the first stage are accepted, using rehearsal. We extensively test and analyze our method on two monolingual and two multilingual benchmarks. Our method reduces forgetting and outperforms state-of-the-art CL approaches for ASR, even when limited to a single utterance per previous task.

Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder

In audiovisual automatic speech recognition (AV-ASR) systems, information fusion of visual features in a pre-trained ASR has been proven as a promising method to improve noise robustness. In this work, based on the prominent Whisper ASR, first, we propose a simple and effective visual fusion method -- use of visual features both in encoder and decoder (dual-use) -- to learn the audiovisual interactions in the encoder and to weigh modalities in the decoder. Second, we compare visual fusion methods in Whisper models of various sizes. Our proposed dual-use method shows consistent noise robustness improvement, e.g., a 35% relative improvement (WER: 4.41% vs. 6.83%) based on Whisper small, and a 57% relative improvement (WER: 4.07% vs. 9.53%) based on Whisper medium, compared to typical reference middle fusion in babble noise with a signal-to-noise ratio (SNR) of 0dB. Third, we conduct ablation studies examining the impact of various module designs and fusion options. Fine-tuned on 1929 hours of audiovisual data, our dual-use method using Whisper medium achieves 4.08% (MUSAN babble noise) and 4.43% (NoiseX babble noise) average WER across various SNRs, thereby establishing a new state-of-the-art in noisy conditions on the LRS3 AV-ASR benchmark. Our code is at https://github.com/ifnspaml/Dual-Use-AVASR