arXiv subjects

Srikanth Madikeri

Publications and source records attributed to Srikanth Madikeri.

At least 19 recordsLinked to original sources

arXiv2026

Text-only adaptation in LLM-based ASR through text denoising

Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet underexplored challenge. Standard fine-tuning of the LLM on the target domain text often disrupts the critical alignment between the speech and text modality learned by the projector, degrading performance. We introduce a novel text-only adaptation method that frames this process as a text denoising task. Our approach trains the LLM to recover clean transcripts from noisy inputs. This process effectively adapts the model to a target domain while preserving cross-modal alignment. Our solution is lightweight, requiring no architectural changes or additional parameters. Extensive evaluation on two datasets demonstrates up to 22.1% relative improvement, outperforming recent state-of-the-art text-only adaptation methods.

cs.SD↗

arXiv2026

The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding

Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video. Processing every frame is infeasible at scale, so systems are constrained to sparse inputs of 8 to 16 frames per video. Yet state-of-the-art multimodal large language models (MLLMs) are pretrained on dense sequences of hundreds of frames, creating a fundamental mismatch between training and deployment conditions. This mismatch causes severe performance collapse: the Qwen3-VL 8B model drops from 56.0% to 22.3% temporal mIoU when frames are reduced to 16, a 60.2% relative degradation. We present a systematic empirical study of training strategies to close this gap for spatial-temporal video grounding. Our results suggest that visual feature extraction is the dominant bottleneck under sparse-frame inputs. Adapting only the final three ViT layers, 4% of total parameters, achieves 68.8% temporal mIoU and surpasses a zero-shot 8B model using dense inputs by 12.8 points. Language model fine-tuning, by contrast, offers negligible or negative returns. A boundary-aware sampling strategy, Hybrid16, further improves temporal mIoU by 26 points over uniform sampling when temporal boundaries are available. We conclude that for sparse-frame video grounding, training strategy dominates model scale: a fine-tuned 2B model consistently outperforms a zero-shot 8B model, with or without dense frame access.

cs.CV↗

arXiv2026

How to Leverage Synthetic Speech for LLM-Based ASR Systems?

In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is an appealing alternative for training automatic speech recognition (ASR) without exposing sensitive customer recordings. Yet a persistent distributional gap between synthetic and real data limits how far it can replace genuine recordings. Prior work largely treats this gap as a black box to be engineered around, but in our work, we instead examine its origin directly by probing a SLAM-ASR architecture. Then, we localise where its LLM backbone separates real from synthetic speech and find the discriminative signal concentrated in the early-to-middle layers, where temporal and prosodic perturbations disrupt it most. We further show that representation-level separability, help, but does not directly predict downstream ASR gains. On the other hand, convolving synthetic audio with room impulse responses (RIRs) narrows the gap not by making synthetic speech sound cleaner or more natural, but by reproducing the acoustic irregularities of real recordings. Translating these findings into the training procedure, by adding a layer-selection module combined with RIR augmentation matches a fully real-data baseline using only 25% of the real speech (13.6h) and surpasses it at all higher proportions.

cs.CL↗

arXiv2026

Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR

Standard LLM-based speech recognition systems typically process utterances in isolation, limiting their ability to leverage conversational context. In this work, we study whether multimodal context from prior turns improves LLM-based ASR and how to represent that context efficiently. We find that, after supervised multi-turn training, conversational context mainly helps with the recognition of contextual entities. However, conditioning on raw context is expensive because the prior-turn audio token sequence grows rapidly with conversation length. To address this, we propose Abstract Compression, which replaces the audio portion of prior turns with a fixed number of learned latent tokens while retaining corresponding transcripts explicitly. On both in-domain and out-of-domain test sets, the compressed model recovers part of the gains of raw-context conditioning with a smaller prior-turn audio footprint. We also provide targeted analyses of the compression setup and its trade-offs.

cs.CL↗

arXiv2026

TidyVoice 2026 Challenge Evaluation Plan

The performance of speaker verification systems degrades significantly under language mismatch, a critical challenge exacerbated by the field's reliance on English-centric data. To address this, we propose the TidyVoice Challenge for cross-lingual speaker verification. The challenge leverages the TidyVoiceX dataset from the novel TidyVoice benchmark, a large-scale, multilingual corpus derived from Mozilla Common Voice, and specifically curated to isolate the effect of language switching across approximately 40 languages. Participants will be tasked with building systems robust to this mismatch, with performance primarily evaluated using the Equal Error Rate on cross-language trials. By providing standardized data, open-source baselines, and a rigorous evaluation protocol, this challenge aims to drive research towards fairer, more inclusive, and language-independent speaker recognition technologies, directly aligning with the Interspeech 2026 theme, "Speaking Together."

eess.AS↗

arXiv2026

Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection

LLM-based automatic speech recognition (ASR), a well-established approach, connects speech foundation models to large language models (LLMs) through a speech-to-LLM projector, yielding promising results. A common design choice in these architectures is the use of a fixed, manually defined prompt during both training and inference. This setup not only enables applicability across a range of practical scenarios, but also helps maximize model performance. However, the impact of prompt design remains underexplored. This paper presents a comprehensive analysis of commonly used prompts across diverse datasets, showing that prompt choice significantly affects ASR performance and introduces instability, with no single prompt performing best across all cases. Inspired by the speech-to-LLM projector, we propose a prompt projector module, a simple, model-agnostic extension that learns to project prompt embeddings to more effective regions of the LLM input space, without modifying the underlying LLM-based ASR model. Experiments on four datasets show that the addition of a prompt projector consistently improves performance, reduces variability, and outperforms the best manually selected prompts.

eess.AS↗

arXiv2026

Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities

Person identification systems often rely on audio, visual, or behavioral cues, but real-world conditions frequently present with missing or degraded modalities. To address this challenge, we propose a multimodal person identification framework incorporating upper-body motion, face, and voice. Experimental results demonstrate that body motion outperforms traditional modalities such as face and voice in within-session evaluations, while serving as a complementary cue that enhances performance in multi-session scenarios. Our model employs a unified hybrid fusion strategy, fusing both feature-level and score-level information to maximize representational richness and decision accuracy. Specifically, it leverages multi-task learning to process modalities independently, followed by cross-attention and gated fusion mechanisms to exploit both unimodal information and cross-modal interactions. Finally, a confidence-weighted strategy and mistake-correction mechanism dynamically adapt to missing data, ensuring that our single classification head achieves optimal performance even in unimodal and bimodal scenarios. We evaluate our method on CANDOR, a newly introduced interview-based multimodal dataset, which we benchmark in this work for the first time. Our results demonstrate that the proposed trimodal system achieves 99.51% Top-1 accuracy on person identification tasks. In addition, we evaluate our model on the VoxCeleb1 dataset as a widely used evaluation protocol and reach 99.92% accuracy in bimodal mode, outperforming conventional approaches. Moreover, we show that our system maintains high accuracy even when one or two modalities are unavailable, making it a robust solution for real-world person recognition applications. The code and data for this work are publicly available.

cs.CV↗

arXiv2026

Spoofing-Aware Speaker Verification via Wavelet Prompt Tuning and Multi-Model Ensembles

This paper describes the UZH-CL system submitted to the SASV section of the WildSpoof 2026 challenge. The challenge focuses on the integrated defense against generative spoofing attacks by requiring the simultaneous verification of speaker identity and audio authenticity. We proposed a cascaded Spoofing-Aware Speaker Verification framework that integrates a Wavelet Prompt-Tuned XLSR-AASIST countermeasure with a multi-model ensemble. The ASV component utilizes the ResNet34, ResNet293, and WavLM-ECAPA-TDNN architectures, with Z-score normalization followed by score averaging. Trained on VoxCeleb2 and SpoofCeleb, the system obtained a Macro a-DCF of 0.2017 and a SASV EER of 2.08%. While the system achieved a 0.16% EER in spoof detection on the in-domain data, results on unseen datasets, such as the ASVspoof5, highlight the critical challenge of cross-domain generalization.

eess.AS↗

arXiv2026

TidyVoice: A Curated Multilingual Dataset for Speaker Verification Derived from Common Voice

The development of robust, multilingual speaker recognition systems is hindered by a lack of large-scale, publicly available and multilingual datasets, particularly for the read-speech style crucial for applications like anti-spoofing. To address this gap, we introduce the TidyVoice dataset derived from the Mozilla Common Voice corpus after mitigating its inherent speaker heterogeneity within the provided client IDs. TidyVoice currently contains training and test data from over 212,000 monolingual speakers (Tidy-M) and around 4,500 multilingual speakers (Tidy-X) from which we derive two distinct conditions. The Tidy-M condition contains target and non-target trials from monolingual speakers across 81 languages. The Tidy-X condition contains target and non-target trials from multilingual speakers in both same- and cross-language trials. We employ two architectures of ResNet models, achieving a 0.35% EER by fine-tuning on our comprehensive Tidy-M partition. Moreover, we show that this fine-tuning enhances the model's generalization, improving performance on unseen conversational interview data from the CANDOR corpus. The complete dataset, evaluation trials, and our models are publicly released to provide a new resource for the community.

eess.AS↗

arXiv2026

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation

We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built around a standardized Dialog representation, SDialog provides: (1) persona-driven multi-agent simulation with composable orchestration for controlled, synthetic dialog generation, (2) comprehensive evaluation combining linguistic metrics, LLM-as-a-judge and functional correctness validators, (3) mechanistic interpretability tools for activation inspection and steering via feature ablation and induction, and (4) audio generation with full acoustic simulation including 3D room modeling and microphone effects. The toolkit integrates with all major LLM backends, enabling mixed-backend experiments under a unified API. By coupling generation, evaluation, and interpretability in a dialog-centric architecture, SDialog enables researchers to build, benchmark and understand conversational systems more systematically.

cs.CL↗

arXiv2025

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation

We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built around a standardized \texttt{Dialog} representation, SDialog provides: (1) persona-driven multi-agent simulation with composable orchestration for controlled, synthetic dialog generation, (2) comprehensive evaluation combining linguistic metrics, LLM-as-a-judge and functional correctness validators, (3) mechanistic interpretability tools for activation inspection and steering via feature ablation and induction, and (4) audio generation with full acoustic simulation including 3D room modeling and microphone effects. The toolkit integrates with all major LLM backends, enabling mixed-backend experiments under a unified API. By coupling generation, evaluation, and interpretability in a dialog-centric architecture, SDialog enables researchers to build, benchmark and understand conversational systems more systematically.

cs.AI↗

arXiv2025

CL-UZH submission to the NIST SRE 2024 Speaker Recognition Evaluation

The CL-UZH team submitted one system each for the fixed and open conditions of the NIST SRE 2024 challenge. For the closed-set condition, results for the audio-only trials were achieved using the X-vector system developed with Kaldi. For the audio-visual results we used only models developed for the visual modality. Two sets of results were submitted for the open-set and closed-set conditions, one based on a pretrained model using the VoxBlink2 and VoxCeleb2 datasets. An Xvector-based model was trained from scratch using the CTS superset dataset for the closed set. In addition to the submission of the results of the SRE24 evaluation to the competition website, we talked about the performance of the proposed systems on the SRE24 evaluation in this report.

eess.AS↗

arXiv2025

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation

Token-based multitasking frameworks like TokenVerse require all training utterances to have labels for all tasks, hindering their ability to leverage partially annotated datasets and scale effectively. We propose TokenVerse++, which introduces learnable vectors in the acoustic embedding space of the XLSR-Transducer ASR model for dynamic task activation. This core mechanism enables training with utterances labeled for only a subset of tasks, a key advantage over TokenVerse. We demonstrate this by successfully integrating a dataset with partial labels, specifically for ASR and an additional task, language identification, improving overall performance. TokenVerse++ achieves results on par with or exceeding TokenVerse across multiple tasks, establishing it as a more practical multitask alternative without sacrificing ASR performance.

cs.CL↗

arXiv2025

Unifying Global and Near-Context Biasing in a Single Trie Pass

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work presents a practical approach to address these challenges through an unexplored combination of an NE bias list and a word-level n-gram language model (LM). This solution balances simplicity and effectiveness, improving entities' recognition while maintaining or even enhancing overall ASR performance. We efficiently integrate this enriched biasing method into a transducer-based ASR system, enabling context adaptation with almost no computational overhead. We present our results on three datasets spanning four languages and compare them to state-of-the-art biasing strategies. We demonstrate that the proposed combination of keyword biasing and n-gram LM improves entity recognition by up to 32% relative and reduces overall WER by up to a 12% relative.

cs.CL↗

arXiv2025

Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering

Fine-tuning pretrained ASR models for specific domains is challenging when labeled data is scarce. But unlabeled audio and labeled data from related domains are often available. We propose an incremental semi-supervised learning pipeline that first integrates a small in-domain labeled set and an auxiliary dataset from a closely related domain, achieving a relative improvement of 4% over no auxiliary data. Filtering based on multi-model consensus or named entity recognition (NER) is then applied to select and iteratively refine pseudo-labels, showing slower performance saturation compared to random selection. Evaluated on the multi-domain Wow call center and Fisher English corpora, it outperforms single-step fine-tuning. Consensus-based filtering outperforms other methods, providing up to 22.3% relative improvement on Wow and 24.8% on Fisher over single-step fine-tuning with random selection. NER is the second-best filter, providing competitive performance at a lower computational cost.

cs.CL↗

arXiv2025

Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering

Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that improves ASR adaptation by filtering pseudo-labels generated using Whisper (encoder-decoder) and Zipformer (transducer) models. Our approach integrates multiple selection strategies -- including word error rate (WER) prediction, named entity recognition (NER), and character error rate (CER) analysis -- to extract high-quality training segments. We evaluate our method on Whisper and Zipformer using a 7500-hour baseline, comparing it to a CER-based approach relying on hypotheses from three ASR systems. Fine-tuning on 7500 hours of pseudo-labeled call center data achieves 12.3% WER, while our filtering reduces the dataset to 100 hours (1.4%) with similar performance; a similar trend is observed on Fisher English.

cs.CL↗

arXiv2024

Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction

Efficiently deriving structured workflows from unannotated dialogs remains an underexplored and formidable challenge in computational linguistics. Automating this process could significantly accelerate the manual design of workflows in new domains and enable the grounding of large language models in domain-specific flowcharts, enhancing transparency and controllability. In this paper, we introduce Dialog2Flow (D2F) embeddings, which differ from conventional sentence embeddings by mapping utterances to a latent space where they are grouped according to their communicative and informative functions (i.e., the actions they represent). D2F allows for modeling dialogs as continuous trajectories in a latent space with distinct action-related regions. By clustering D2F embeddings, the latent space is quantized, and dialogs can be converted into sequences of region/action IDs, facilitating the extraction of the underlying workflow. To pre-train D2F, we build a comprehensive dataset by unifying twenty task-oriented dialog datasets with normalized per-turn action annotations. We also introduce a novel soft contrastive loss that leverages the semantic information of these actions to guide the representation learning process, showing superior performance compared to standard supervised contrastive loss. Evaluation against various sentence embeddings, including dialog-specific ones, demonstrates that D2F yields superior qualitative and quantitative results across diverse domains.

cs.CL↗

arXiv2024

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are trained with full attention context. In this paper, we introduce XLSR-Transducer, where the XLSR-53 model is used as encoder in transducer setup. Our experiments on the AMI dataset reveal that the XLSR-Transducer achieves 4% absolute WER improvement over Whisper large-v2 and 8% over a Zipformer transducer model trained from scratch. To enable streaming capabilities, we investigate different attention masking patterns in the self-attention computation of transformer layers within the XLSR-53 model. We validate XLSR-Transducer on AMI and 5 languages from CommonVoice under low-resource scenarios. Finally, with the introduction of attention sinks, we reduce the left context by half while achieving a relative 12% improvement in WER.

eess.AS↗