Speech
-
Listen-to-Reason: Listen with Experts, Retrieve over a Graph, Reason with LLMs
2026-10-07 18:14:58Pooneh Mousavi, Mirco Ravanelli, Cem SubakanAbstract
Large audio-language models (LALMs) fuse an audio encoder into a large language model (LLM) through multi-stage training. This coupling means that a new domain or a stronger LLM requires retraining, and their answers cannot be traced to what the model heard: a chain-of-thought is a post-hoc account. We propose Listen-to-Reason (L2R), an interpretable-by-design pipeline that passes audio to the LLM through an explicit, human-readable tree: small heads on frozen expert encoders map each chunk of a clip to semantically meaningful nodes on the tree (for speech, music and environmental sound), and a frozen text-only LLM answers from these nodes and an ASR transcript without hearing the clip. Every answer can therefore be traced to the nodes and transcript it read, and the nodes are causal: replacing the deciding node with a distractor overturns 78% of correct answers on SAKURA. With a 7B reader, L2R outperforms all LALMs we compare against on SAKURA and trails them by 6-12 points on MMAU and MMAR, despite training about 1,400x fewer parameters on orders of magnitude less audio data. However, because any LLM can serve as the reader, we show that a stronger reader narrows this gap without retraining any audio component. A new domain is added with one small head: with five labelled clips per species, it outperforms QLoRA fine-tuning of an LALM on the same clips by 13-26 points.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10749
PDF
-
MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive Screening
2026-10-07 17:19:46Duy-Cat Can, Mau Minh Phuc Le, Tuan-Khoa Hoang, Hai-Dang Nguyen, Trung-Hieu Do, Dang Minh Ly, Minh-Duc Nguyen, Nghia TT Hoang, Linh-Trung Nguyen, Huy-Hieu Pham, Huong Ha, Binh T. Nguyen, Oliver Y. Ch\'enAbstract
MemoCare is an interactive mobile system for automated multimodal cognitive screening. A React Native application combines spoken responses, temporal and spatial orientation, touchscreen actions, and visuoconstruction in complete English and Vietnamese workflows. Speech is transcribed by Google Speech-to-Text and scored locally with deterministic task-specific natural language processing rules; GPS coordinates are resolved by the MemoCare spatial module before answer matching; touch tasks are scored from interaction events; and the drawing task uses a three-model convolutional neural network consensus with separate visual interpretation. Software tests pass 151/151 predefined cases across speech/language, spatial-answer, and touch-interaction scoring, while spatial regression passes 48/48 four-country coordinate-resolution cases. For the drawing module, validation-selected ShuffleNetV2 x1.5 achieved 91.33% mean balanced accuracy and 78.87% exact three-criterion accuracy on a locked 71-image test set. Four clinician co-authors additionally inspected the end-to-end workflow, yielding a pooled median rating of 4/5 across eight criteria, with item-level medians ranging from 3 to 4.5. At MMM, attendees can directly try a shortened multimodal screening workflow and inspect automatic item-level and total scoring.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10448
PDF
-
Steerspeech: Activation Steering For Emotion Control In Generated Speech
2026-10-07 16:56:56Afsara Benazir, Darius P\'etermann, Felix Xiaozhu Lin, Salar RahiliAbstract
Pretrained text-to-speech (TTS) models can generate expressive speech, but reliable inference-time emotion control remains challenging: prompts and reference audio offer coarse, inconsistent control, whereas specialized conditioning and model adaptation require costly training. We present SteerSpeech, a lightweight activation-steering framework that controls emotion by injecting steering vectors into hidden activations. For each target emotion we train a lightweight low-rank transform, using a multi-expert objective that encourages monotonic emotion control while preserving speaker identity and linguistic content, constraining steering drift, and keeping the TTS backbone frozen. To optimize through discrete speech tokens, we introduce a two-pass generation-and-replay pipeline using a straight-through estimator to backpropagate expert supervision through sampled tokens. At inference, a target-emotion steering direction is optimized with its respective transform and injected into the base TTS model. Objective and subjective evaluations with Qwen3-TTS across seen, unseen, and accented speakers show stronger continuous emotion control with limited speaker and content degradation. SteerSpeech achieves 1.08x-7.12x baseline target-emotion scores and for a representative emotion subjectively, it receives 78.1%-96.8% intensity preference and 1.43x-1.46x speaker-identity preservation at high steering strengths.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10415
PDF
-
CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing
2026-10-07 15:36:56William Chen, Prem Seetharaman, Ke Chen, Oriol Nieto, Kevin Duarte, Siddharth Srinivasan Iyer, Mamshad Nayeem Rizve, Zhiwen Cao, Shinji Watanabe, Yuanjun Xiong, Jianming Zhang, Zeyu Jin, Justin SalamonAbstract
Multimedia editing requires generative models to interpret complex, compositional instructions and modify only the desired elements across modalities, a capability largely beyond existing systems. Current approaches are typically limited to simple, single-attribute edits within one modality, since diverse, high-quality editing pairs are hard to obtain, especially for cross-modal tasks where aligned audiovisual (AV) data is scarce. We present CrossEdit, a unified omni-modal editing model for images, audio, and video that performs AV movie scene edits zero-shot through cross-modal transfer. Our key observation is that complex instruction-following, once learned in any modality, generalizes to others. We exploit the additive nature of acoustic signals to procedurally generate large-scale audio editing pairs with compositional instructions, and show that fine-tuning on this synthetic data and self-supervised AV masked reconstruction, alongside a targeted set of curated cross-modal tasks, induces instruction-following that transfers zero-shot to unseen modality and instruction combinations. To evaluate this capability, we release CrossEditBench, a human-annotated benchmark of AV edits on movie scenes, and propose AV-FES, a metric that jointly scores instruction following and consistency. We show that our proposed techniques improve performance on zero-shot AV movie scene editing, while maintaining or improving performance on lip-synced speech editing and standard image, video, and audio editing benchmarks. Demos are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10264
PDF
-
InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews
2026-10-07 14:23:32Patrick Schrottenbacher, Leon Hammerla, Lydia Kleine, Doris Stingl, Alexander MehlerAbstract
We present InterView-C, a German multimodal corpus of 27 survey interviews conducted entirely in virtual reality, with both interlocutors represented by avatars. The corpus aligns spoken interaction with synchronized behavioral data, including gaze, head and body movement, facial behavior, hand and finger tracking. Its reference transcripts and linguistic annotations provide a reliable interface between this multimodal spoken interaction and predominantly text-based NLP methods. This interface is important because automatically transcribing speech can distort linguistically relevant information, while downstream models trained on existing resources may additionally face transfer challenges when applied to transcribed spoken data. InterView-C therefore provides word-timed and manually post-edited verbatim transcripts for all 54 recordings, interview-item timings, questionnaire responses and negation cue and scope annotations for 1,422 sentences, 1,398 of them doubly annotated ({\alpha}=0.87 for cues; {\alpha}=0.81 for scopes). We demonstrate both challenges empirically: nine open-weight ASR systems disproportionately misrecognize short closed answers and number words, while negation models trained on existing corpora show lower and highly variable performance on our transcribed interviews than a model trained on the InterView-C annotations. InterView-C thus enables linguistic analyses of spoken interaction while retaining their alignment with rich multimodal behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10145
PDF
-
DuRe-ST: Dual-Relation Spectro-Temporal Modeling for Speech Deepfake Detection
2026-10-07 14:04:59Shaole Li, Siqing Qin, Youzhi Tu, Kong Aik LeeAbstract
Previous speech deepfake detectors can adaptively capture spectro-temporal dependencies through graph attention, yet they largely overlook the co-variation between spectral and temporal representations. To address this gap, we construct a normalized affinity graph from their joint covariance and apply polynomial graph filtering to capture higher-order covariance-induced dependencies. We first develop Cov-ST to isolate the contribution of covariance-based relational modeling. Although it improves detection performance, its sensitivity to the polynomial order suggests limited robustness when covariance relations are modeled alone. We therefore propose DuRe-ST, which jointly exploits covariance-induced and graph-attention-induced relations to capture complementary second-order co-variation and adaptive spectro-temporal dependencies. Experiments show that DuRe-ST achieves an average relative EER reduction of 25.9% over XLSR-AASIST on the ASVspoof benchmarks and 28.4% across four cross-dataset benchmarks with only 4-8k additional trainable back-end parameters. It further outperforms the strongest publicly available comparison models by 2.2-13.2% in relative EER on four benchmarks, while remaining smaller than the publicly available models considered.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10121
PDF
-
Training-Free Instruction TTS Gender Bias Calibration Using Model-Adaptive Steering
2026-10-07 10:51:38Kuan-Yu Chen, Yi-Cheng Lin, Jeng-Lin Li, Jian-Jiun DingAbstract
Instruction text-to-speech (ITTS) systems systematically encode acoustic gender skews from descriptive style prompts, such as occupations or personas, even when demographic attributes are left unspecified. Calibrating the implicit gender distribution of the synthesized voices, across heterogeneous architectures and without model retraining or overriding explicit user prompts, is an open problem. In this work, we propose \textit{model-adaptive steering}, a training-free bias calibration method that steers post-encoder conditioning representations using a group deviation vector paired with a coarse-to-fine strength search on a development set. A deterministic lexical gate bypasses intervention whenever explicit gender keywords are detected, preserving intended prompt semantics. Evaluated on a 12,800-prompt held-out benchmark across four ITTS models (three architectures), the proposed method reduces aggregate calibration error from 11.5--28.1 to 0.8--5.9 percentage points (e.g., shifting Parler-TTS Mini from 78.1\% and PromptTTS++ from 27.3\% female to 50.8--52.4\%). Output rates stay within 0.9 pp across anchor set sizes at fixed operating points, while UTMOS decreases by at most 0.08 and WER degrades by at most 3.3 pp.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09831
PDF
-
Backdooring Acoustic Foundation Models for Physically Realizable Triggers
2026-10-07 10:41:54Zebin Yun, Eyal Ronen, Mahmood SharifAbstract
Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with minimal resources. However, the security of applications based on AFMs remains largely underexplored. Our work addresses this gap by proposing the Foundation Acoustic model Backdoor (FAB) attack, demonstrating that state-of-the-art AFMs are susceptible to backdooring under practical settings. Despite making minimal assumptions about adversary capabilities (e.g., no access to pre-training data), we show that FAB preserves benign performance while inducing backdoors that survive fine-tuning and cause significant degradation across diverse downstream tasks when activated. Notably, FAB utilizes task-agnostic, physically realizable, inconspicuous, and sync-free triggers (e.g., a background siren). We evaluate FAB using two leading AFMs, nine downstream tasks, and four different triggers. We further demonstrate its effectiveness against established defenses and across both digital and physical domains. While extensive end-to-end fine-tuning can mitigate FAB, such a defense is resource-intensive and task-specific. Our work highlights critical risks to AFMs and calls for advanced defenses.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09819
PDF
-
A multi-scenario EEG dataset for auditory attention decoding in naturalistic multi-talker environments
2026-10-07 06:39:56Shu Peng, Rui Liu, Yufei Zhang, Wenlong You, Zhige Chen, Jiachen Xi, Qiyuan Sun, Yan Liu, Kay Chen Tan, Jibin WuAbstract
Understanding how the brain selectively follows relevant speech amid competing voices is a central challenge in auditory neuroscience and a key step toward neuro-steered hearing technologies. However, most open-source Electroencephalography (EEG) datasets for Auditory Attention Decoding (AAD) use idealized single-competing-talker paradigms that oversimplify the acoustic, spatial, and semantic structure of everyday communication. To capture this ecological complexity, we introduce the SoundBubble-EEG dataset: a high-density 128-channel EEG resource comprising more than 25 hours of recordings from 30 participants. The paradigm requires listeners to selectively attend to a dynamic target speaker group, a designated "sound bubble", amid competing multi-speaker distractor bubbles across three realistic scenarios: a restaurant, a home TV viewing, and a meeting discussion. By bridging the gap between constrained laboratory protocols and real-world auditory scenes, this dataset enables investigations of multi-talker speech comprehension, neural speech tracking, and cross-scenario generalization. It also provides a benchmark for AAD algorithms under realistic acoustic and semantic variability and may support auditory neuroscience and the development of neuro-steered hearing technologies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09539
PDF
-
Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification
2026-10-07 05:42:40Minu Kim, Jihwan Lee, David R. Mortensen, Shrikanth NarayananAbstract
Spoken language identification (LID) aims to recognize the target language regardless of accent. In practice, however, LID models fine-tuned from self-supervised speech representations frequently confuse accents with languages, misclassifying non-native (L2) speech as the speaker's first language (L1). We show that non-native speech representations lie between native target-language and native L1 poles, causing systematic misclassification. To address this, we introduce a geometric projection that estimates an L1-bias direction solely from native speech and removes it before the frozen LID head. Across five MMS-LID models and non-native corpora, this projection substantially improves target language identification for L2-accented speech while preserving predictions for native speech. These results show that accent-induced L1 bias can be corrected directly within the representation space without L2 training data or model adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09486
PDF
-
Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented Languages
2026-10-07 05:23:18Muhammad Huzaifah, Yu Pan, Zachary Yeo, Ningjie Bai, Guangzhao YangAbstract
Contextual biasing supplies an ASR system with a list of expected words at inference time, but existing methods rely on word boundaries that Japanese and Chinese do not provide. We present a boundary-free biasing decoder for frozen public CTC models, built on a character-level Aho-Corasick automaton, with no training and no second pass. Two evidence-based mechanisms replace the boundary: a depth-adaptive gate that sets how hard to push from match depth, and reading-space matching for when the audio is right but the characters are wrong. On Aishell-1 NE's hard R1 subset we reach 66.5% recall, above the trained CLAS baseline (64%), transferring to WenetSpeech and to a second architecture without retuning. We release the first open Japanese contextual-biasing benchmark, where biasing lifts rare-word recall by 25 points at precision above 97%, and still by 19 and 22 points against 1,000-word lists.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09467
PDF
-
BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech
2026-10-07 05:22:19Rohit Kumar Sen, Anik ChowdhuryAbstract
Political discourse often uses rhetorical and persuasive language to frame narratives, influence public opinion, and mobilize audiences. While Bangla natural language processing has made progress in sentiment analysis and opinion mining, systematic benchmarking of transformer models for fine-grained rhetorical and persuasion technique detection in Bangla political speech remains largely underexplored. This paper presents a benchmark study of transformer-based models for detecting rhetorical form and persuasive intent in Bangla political discourse. Using BanglaRhet, a manually annotated corpus of 30,289 Bangla political speech segments collected from publicly available political news sources, we formulate two supervised single-label classification tasks: rhetorical technique detection (contrast, repetition, exaggeration, metaphor, rhetorical questions) and persuasion technique detection (blame assignment, call to action, unity call, moral, emotional, and logical appeals). We evaluate four transformer-based models, BanglaBERT, BanglaBERT-Base, SahajBERT, and XLM-RoBERTa-Base, against classical TF-IDF baselines. BanglaBERT achieves the highest performance, with 65.40% macro-F1 for rhetorical technique detection and 66.46% for persuasion technique detection, outperforming the best tuned classical baseline by 19.2 and 13.8 macro-F1 points, respectively. Class-level analysis indicates that errors are mainly associated with semantic overlap among labels, figurative language, and class imbalance. The results provide initial benchmark baselines for Bangla rhetorical and persuasion-aware political discourse analysis and highlight the need for context-aware and multi-label modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09464
PDF
-
Beyond Token Revision: Investigating Mask-and-Replace Diffusion for Zero-Shot Text-to-Speech
2026-10-07 05:00:25Hounsu Kim, Joonyong Park, Yuki Saito, Satoru Fukayama, Juhan NamAbstract
Unlike autoregressive models, discrete diffusion-based models for zero-shot text-to-speech generate speech tokens in parallel and can revisit earlier predictions. Mask-and-replace training extends mask-only training by randomly replacing some tokens, and its gains are commonly attributed to self-correction, the ability to revise previously generated tokens. However, exposure to randomly perturbed context during training may itself improve generation, raising the question of whether these gains require inference-time token revision. To investigate this question, we use DeMaR, which combines mask-and-replace training with confidence-ranked mask-only sampling while preserving the total training corruption probability. Trained from scratch on LibriTTS, DeMaR achieves lower word error rates (WER) than autoregressive and mask-only diffusion baselines using the same speech tokenizer. This advantage persists when each token remains unchanged after first being unmasked. Matched training conditions on two heterogeneous speech tokenizers show that both noisy-context augmentation and replacement supervision improve WER under this restriction. These findings demonstrate training-side benefits of replacement beyond enabling inference-time token revision.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09448
PDF
-
IVG-UAV: An Intelligent Voice-Guided UAV System for Autonomous Ripe Fruit Harvesting with Vision-Based Classification and Adaptive Path Planning
2026-10-07 03:59:03Dinh Trung DuongAbstract
In tropical regions, their agricultural sectors remain highly dependent on manual labor for fruit harvesting. On large-scale farms, this dependency often results in significant labor cost and logistic complexities. This project presents the development and simulation of a voice-controlled Unmanned Aerial Vehicle (UAV) system designed to automate harvesting tasks in extensive plantations. The proposed system integrates speech recognition using Whisper [1] and LLM, computer vision-based ripeness classification, and adaptive path planning within a unified framework. The entire system is modeled and validated in a Gazebo simulation environment, allowing performance evaluation under controlled agricultural scenarios
Abstract (translated)
URL
https://arxiv.org/abs/2610.09398
PDF
-
VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation
2026-10-07 02:50:56Jingqi Sun, Haozhan Tang, Shulin He, Zhong-Qiu WangAbstract
Blind Source Separation(BSS) is a fundamental problem in signal processing, aiming to separate multiple source signals from their mixtures without prior knowledge of the sources or the mixing process. Traditional approaches, such as Independent Vector Analysis (IVA) exploits statistical independence of sources. Recently, diffusion-based approaches have emerged as a promising alternative by leveraging powerful generative priors. Among them, ArrayDPS formulates BSS problem as a posterior sampling problem, and utilizes a pretrained speech diffusion model to guide the recovery of clean source signals. A key factor behind its separation capability is the multi-channel consistency (MC) objective, which enforces the estimated source signals to reconstruct the observed microphone mixtures through the estimated acoustic transfer functions. However, the number of microphones in the array is often limited, which constrains the performance of ArrayDPS. To address this issue, we propose VM-ArrayDPS, a novel method that augments the microphone array with virtual microphones with higher-SNR, these microphones can offer extra MC constraints to enhance the separation performance. Experimental results demonstrate that VM-ArrayDPS significantly outperforms ArrayDPS on both 2-speaker and 3-speaker datasets, showcasing the effectiveness of virtual microphone augmentation in improving BSS performance. We also did ablation studies to show the influence of the number of virtual microphones and weight of the MC objective brought by virtual microphones.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09334
PDF
-
Dialect-Robust Speech Language Models with Synthetic Pseudo-Dialect Augmentation
2026-10-07 02:25:43Shunsuke Mitsumori, Tomoya Mizumoto, Yusuke FujitaAbstract
Speech Language Model (SLM) performance often degrades on dialects due to data scarcity. Conventional text-to-speech (TTS) augmentation struggles to cover diverse dialects as it requires a certain amount of real dialect speech. We propose synthesizing pseudo-dialect speech by converting LLM-generated dialect text via a standard-language TTS model, requiring zero real dialect speech. Additionally, we introduce intermediate standard-text prediction during training, acting as semantic normalization for downstream tasks. We evaluate dialect understanding via dialect-to-English speech translation across Japanese, German, and Chinese dialects. Compared to synthetic standard speech baselines, pseudo-dialect augmentation improves scores for Japanese (from 25.38 to 26.24) and German (from 31.57 to 32.47). Furthermore, the intermediate standard-text prediction effectively bridges the semantic gap, boosting performance to 28.26 for Japanese and from 11.67 to 16.37 for Chinese. These results suggest that our approach scales to various languages without requiring speech resources specific to each dialect.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09321
PDF
-
Lyapunov-Inspired LyRIC Activation and GLARE Attention in Chaos-Guided State Space Modeling for EMG-To-Speech Synthesis
2026-10-06 23:39:45Sajid Fardin Dipto, Tarikul Islam Tamiti, Luke Baja-Ricketts, David Vergano, Anomadarshi BaruaAbstract
Electromyography-to-Speech (ETS) synthesis is typically a non-linear, chaotic dynamical system. However, no prior work has studied the chaotic behavior of ETS synthesis to date. Yet, prior works strictly rely on standard reconstruction metrics with parameter-heavy transformers that systematically over-smooth natural acoustic dynamics. To close this gap, for the first time, we propose a chaos-inspired Lyapunov-derived activation function (LyRIC) with two novel chaotic loss functions, Lyapunov Exponent Regularization and Multi-Scale Detrended Fluctuation Analysis, to explicitly capture the deterministic chaos of human phonation. In addition, we introduce a compressed novel encoder, GLAME, which synergizes global Mamba state-space modeling with localized GLARE attention. We comprehensively perform frame-level acoustic evaluation in a multilingual and multi-speaker setup using English and Mandarin datasets. The proposed system outperforms the established baseline with a 4.69x increase in objective intelligibility (STOI: 0.61 vs. 0.13) and a 2.08x improvement in spectral reconstruction (LSD: 1.08 vs. 2.25). Importantly, this improvement is achieved with 73.49% fewer parameters (14.34M vs. 54.10M), establishing a new baseline for ETS synthesis. To the best of our knowledge, this is the first work demonstrating that integrating non-linear chaotic physics into neural networks yields superior yet compact inductive biases for real-time ETS synthesis.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09225
PDF
-
PVSync: A Unified Lip-Sync Expert for Timing and Articulation
2026-10-06 23:36:54Kevin Stephen, Varun Menon, Timo Mertens, Nikita DrobyshevAbstract
Lip movements can match the timing of speech without matching the spoken sounds. We introduce PVSync, a unified model for audio-visual offset estimation and phoneme-level articulation scoring. PVSync combines window-level contrastive learning for synchronisation with a phoneme-level articulation objective that aligns audio and video embeddings of the same viseme class across clips. Visemes group phonemes with similar visible articulation. Viseme labels are derived automatically from forced-aligned transcripts, without manual annotations. On offset-corrected videos from 13 talking-head video generation models, PVSync matches human rankings of lip-sync quality more closely than LSE-C, achieving a Spearman correlation of 0.83 versus 0.34. On an automatically constructed benchmark from held-out speech, PVSync distinguishes viseme-matched from mismatched audio-visual pairs with an ROC AUC of 0.91. PVSync also outperforms SyncNet and MTD-VocaLiST in temporal offset recovery on held-out in-the-wild clips. Code and benchmark data will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09223
PDF
-
BanglaBox: A Phonetically-Balanced Corpus and Data-Efficient Foundation-Model Adaptation for Bangla Text-to-Speech with Zero-Shot Voice Cloning
2026-10-06 23:13:22Emtiaz Uddin Ahmed, Araf Mahmud, Sajib Hossain, Tarikul Islam Tamiti, Sajid Fardin Dipto, Anomadarshi BaruaAbstract
We present a recipe for adapting English-pretrained autoregressive TTS foundation models to underrepresented languages, demonstrated on Bangladeshi Bangla. Existing Bangla TTS corpora are small and single-speaker, and to our knowledge no open zero-shot voice-cloning system is available for the Bangladeshi register. We contribute a phonetically- and gender-balanced two-tier Bangladeshi Bangla corpus balanced via a tiered Jensen-Shannon divergence objective over conjunct clusters (juktakkhor), together with three fine-tuning changes: a merge-consistent tokenizer extension, Bangla text normalization, and a prompt-masked dual-loss objective. These changes preserve zero-shot cloning across the language switch. Our BanglaEval protocol applies Wilcoxon signed-rank tests with Bonferroni correction over native-speaker ratings. BanglaBox attains near-natural Naturalness, outperforms commercial and open-source baselines on Naturalness, Speaker Similarity, and Clarity, and reaches speaker similarity comparable to prior few-shot results while using approximately 7x less Bangla fine-tuning audio. We further validate the recipe beyond our own test split using a seven-category stress set of difficult real-world text, the public BnTTS evaluation benchmarks, and naturally occurring Bangla that no language model wrote. All artifacts, including the corpus, weights, code, and complete evaluation materials, are released publicly and unconditionally.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09211
PDF
-
SwinDS-BWE: A Parameter-Efficient Swin-1D Lattice Generator with Decision-Science Discriminators for Speech Bandwidth Extension
2026-10-06 22:39:17Tarikul Islam Tamiti, Sajid Fardin Dipto, Luke Baja-Ricketts, David Vergano, Anomadarshi BaruaAbstract
We propose SwinDS-BWE, a decision-science-inspired bandwidth extension (BWE) model with two coupled contributions: (1) Swin Transformers with lattice-style cross-stream interaction yield locality-aware modeling with linear-in-sequence per-window attention cost and reduce the prior AP-BWE generator size 0.5x from 33M to 17M. (2) Three novel lightweight decision-science-inspired discriminators augment AP-BWE's performance: a CVaR discriminator tail-pools activations to emphasize worst high-frequency (HF) segments, a Chance-Constraint HF discriminator penalizes excessive HF energy via a differentiable barrier, and a Multi-Criteria Utility discriminator learns convex style weights over spectral criteria. SwinDS-BWE surpasses prior AP-BWE with a 30x smaller discriminator (42.3M vs. 1.36M) and higher fidelity on English and French datasets. This work shows that decision-science-inspired critics can supervise BWE to reduce discriminator size.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09189
PDF
