Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio understanding to qualify as generally intelligent. However, evaluating auditory intelligence comprehensively remains challenging. To address this gap, we introduce MMAU-Pro, the most comprehensive and rigorously curated benchmark for assessing audio intelligence in AI systems. MMAU-Pro contains 5,305 instances, where each instance has one or more audios paired with human expert-generated question-answer pairs, spanning speech, sound, music, and their combinations. Unlike existing benchmarks, MMAU-Pro evaluates auditory intelligence across 49 unique skills and multiple complex dimensions, including long-form audio comprehension, spatial audio reasoning, multi-audio understanding, among others. All questions are meticulously designed to require deliberate multi-hop reasoning, including both multiple-choice and open-ended response formats. Importantly, audio data is sourced directly ``from the wild" rather than from existing datasets with known distributions. We evaluate 22 leading open-source and proprietary multimodal AI models, revealing significant limitations: even state-of-the-art models such as Gemini 2.5 Flash and Audio Flamingo 3 achieve only 59.2% and 51.7% accuracy, respectively, approaching random performance in multiple categories. Our extensive analysis highlights specific shortcomings and provides novel insights, offering actionable perspectives for the community to enhance future AI systems' progression toward audio general intelligence. The benchmark and code is available at https://sonalkum.github.io/mmau-pro.

Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand, Sonal Kumar, Sreyan Ghosh, Ramani Duraiswami, Chirag Agarwal, Dinesh Manocha. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Open-vocabulary audio-language models, like CLAP [1], offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categories specified with natural language prompts. In this paper, we propose a simple but effective method to improve ZSAC with CLAP. Specifically, we shift from the conventional method of using prompts with abstract category labels (e.g., Sound of an organ) to prompts that describe sounds using their inherent descriptive features in a diverse context (e.g., The organ’s deep and resonant tones filled the cathedral.). To achieve this, we first propose ReCLAP, a CLAP model trained with rewritten audio captions for improved understanding of sounds in the wild. These rewritten captions describe each sound event in the original caption using their unique discriminative characteristics. ReCLAP outperforms all baselines on both multi-modal audio-text retrieval and ZSAC. Next, to improve zero-shot audio classification with ReCLAP, we propose prompt augmentation. In contrast to the traditional method of employing hand-written template prompts, we generate custom prompts for each unique label in the dataset. These custom prompts first describe the sound event in the label and then employ them in diverse scenes. Our proposed method improves ReCLAP’s performance on ZSAC by 1%-18% and outperforms 1 all baselines by 1% - 55%1.

Underwater image enhancement is crucial for marine engineering and aquatic robotics. However, most recent methods have focused on ocean environments, where they trained and tested on oceanic images. As a result, these methods are less effective in river water, where relatively blurry images are produced due to extensive muddy environments. In river water-based image restoration, we have observed two main limitations: (1) the lack of datasets that accurately represent the muddy water conditions found in river environments and (2) the limited effectiveness of current enhancement models in dealing with the unique challenges of muddy water images. To address these limitations, we introduce the "River-GEM" framework, which includes (1) a dataset of highly degraded muddy water images generated using a principle component analysis-based fusion technique and (2) a novel enhancement model utilizing the depth-map guidance to learn complex contextual details of muddy water images. The proposed model captures the intricate details of the objects in degraded images by analyzing feature correlation at multiple scales. Our model shows improvements of 3.42% in SSIM and 5.04% in PSNR over existing methods on the muddy-UIEB dataset. This dataset and enhancement network marks a significant step forward in this area of research. The dataset and code will be available at: https://github.com/Alik033/River-GEM.

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this paper, we first investigate the root causes of hallucinations in LVLMs. Our findings reveal that existing mitigation techniques primarily reduce hallucinations for visual recognition prompts—those that require simple descriptions of visual elements—but fail for cognitive prompts that demand deliberate reasoning. We identify the core issue as a lack of true visual perception in LVLMs: although they can accurately recognize visual elements, they struggle to fully interpret these elements in the context of the input prompt and effectively link this recognition to their internal knowledge, which is critical for reasoning. To address this gap, we introduce Visual Description Grounded Decoding (VDGD), a simple, robust, and training-free method designed to enhance visual perception and improve reasoning capabilities in LVLMs. VDGD works by first generating a detailed description of the image and appending it as a prefix to the instruction. During response generation, tokens are sampled based on their KL divergence to the description, favoring candidates with lower divergence. Experimental results on multiple visual reasoning benchmarks and LVLMs demonstrate that VDGD consistently outperforms existing baselines 2% - 33%. Finally, we introduce VaLLu, a benchmark designed for comprehensive evaluation of the cognitive capabilities of LVLMs.

We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. Our goal is to improve audio classification accuracy with limited labeled data. Traditional data augmentation techniques, which apply artificial transformations (e.g., adding random noise or masking segments), struggle to create data that captures the true diversity present in real-world audios. To address this shortcoming, we propose to augment the dataset with synthetic audio generated from text-to-audio (T2A) diffusion models. However, synthesizing effective augmentations is challenging because not only should the generated data be acoustically consistent with the underlying small-scale dataset, but they should also have sufficient compositional diversity. To overcome the first challenge, we align the generations of the T2A model with the small-scale dataset using preference optimization. This ensures that the acoustic characteristics of the generated data remain consistent with the small-scale dataset. To address the second challenge, we propose a novel caption generation technique that leverages the reasoning capabilities of Large Language Models to (1) generate diverse and meaningful audio captions and (2) iteratively refine their quality. The generated captions are then used to prompt the aligned T2A model. We extensively evaluate Synthio on ten datasets and four simulated limited-data settings. Results indicate our method consistently outperforms all baselines by 0.1%-39% using a T2A model trained only on weakly-captioned AudioSet.

The ability to comprehend audio—which includes speech, non-speech sounds, and music—is crucial for AI agents to interact effectively with the world. We present MMAU, a novel benchmark designed to evaluate multimodal audio understanding models on tasks requiring expert-level knowledge and complex reasoning. MMAU comprises 10k carefully curated audio clips paired with human-annotated natural language questions and answers spanning speech, environmental sounds, and music. It includes information extraction and reasoning questions, requiring models to demonstrate 27 distinct skills across unique and challenging tasks. Unlike existing benchmarks, MMAU emphasizes advanced perception and reasoning with domain-specific knowledge, challenging models to tackle tasks akin to those faced by experts. We assess 18 open-source and proprietary (Large) Audio-Language Models, demonstrating the significant challenges posed by MMAU. Notably, even the most advanced Gemini 2.0 Flash achieves only 59.93% accuracy, and the state-of-the-art open-source Qwen2-Audio achieves only 52.50%, highlighting considerable room for improvement. We believe MMAU will drive the audio and multimodal research community to develop more advanced audio understanding models capable of solving complex audio tasks.

Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce Audio Flamingo 2 (AF2), an Audio-Language Model (ALM) with advanced audio understanding and reasoning capabilities. AF2 leverages (i) a custom CLAP model, (ii) synthetic Audio QA data for fine-grained audio reasoning, and (iii) a multi-stage curriculum learning strategy. AF2 achieves state-of-the-art performance with only a 3B parameter small language model, surpassing large open-source and proprietary models across over 20 benchmarks. Next, for the first time, we extend audio understanding to long audio segments (30 secs to 5 mins) and propose LongAudio, a large and novel dataset for training ALMs on long audio captioning and question-answering tasks. Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert-annotated benchmark for evaluating ALMs on long audio understanding capabilities. We conduct extensive ablation studies to confirm the efficacy of our approach.

Sonal Kumar, Sreyan Ghosh, Utkarsh Tyagi, Anton Jeran Ratnarajah, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Ashish Seth, Ramaneswaran Selvakumar, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the model to do chain-of-thought-type reasoning before answering; (iii) multi-turn, multi-audio chat; (iv) long audio understanding and reasoning (including speech) up to 10 minutes; and (v) voice-to-voice interaction. To enable these capabilities, we propose several large-scale training datasets curated using novel strategies, including AudioSkills-XL, LongAudio-XL, AF-Think, and AF-Chat, and train AF3 with a novel five-stage curriculum-based training strategy. Trained on only open-source audio data, AF3 achieves new SOTA results on over 20+ (long) audio understanding and reasoning benchmarks, surpassing both open-weight and closed-source models trained on much larger datasets.

Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Chandra Kiran Evuru, Ramaneswaran S, S Sakshi, Dinesh Manocha. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to accurately estimate the RIR from a given reverberant speech signal and the visual cues of its corresponding environment. AV-RIR builds on a novel neural codec-based architecture that effectively captures environment geometry and materials properties and solves speech dereverberation as an auxiliary task by using multi-task learning. We also propose Geo-Mat features that augment material information into visual cues and CRIP that improves late reverberation components in the estimated RIR via image-to-RIR retrieval by 86%. Empirical results show that AV-RIR quantitatively outperforms previous audio-only and visual-only approaches by achieving 36% - 63% improvement across various acoustic metrics in RIR estimation. Additionally, it also achieves higher preference scores in human evaluation. As an auxiliary benefit, dereverbed speech from AV-RIR shows competitive performance with the state-of-the-art in various spoken language processing tasks and outperforms reverberation time error score in the real-world AVSpeech dataset. Qualitative examples of both synthesized reverberant speech and enhanced speech are available online11https://anton-jeran.github.io/AVRIR/.

Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, S Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

In this paper, we present EH-MAM (Easyto-Hard adaptive Masked Acoustic Modeling), a novel self-supervised learning approach for speech representation learning.In contrast to the prior methods that use random masking schemes for Masked Acoustic Modeling (MAM), we introduce a novel selective and adaptive masking strategy.Specifically, during SSL training, we progressively introduce harder regions to the model for reconstruction.Our approach automatically selects hard regions and is built on the observation that the reconstruction loss of individual frames in MAM can provide natural signals to judge the difficulty of solving the MAM pre-text task for that frame.To identify these hard regions, we employ a teacher model that first predicts the frame-wise losses and then decides which frames to mask.By learning to create challenging problems, such as identifying harder frames and solving them simultaneously, the model is able to learn more effective representations and thereby acquire a more comprehensive understanding of the speech.Quantitatively, EH-MAM outperforms several state-ofthe-art baselines across various low-resource speech recognition and SUPERB benchmarks by 5%-10%.Additionally, we conduct a thorough analysis to show that the regions masked by EH-MAM effectively capture useful context across speech frames 1 . * Equal contribution, † Equal Ideation 1 Code:

We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore. Additionally, our proposed method can transfer to any domain without the need for any additional fine-tuning. To generate a caption for an audio sample, we leverage an audio-text model CLAP [1] to retrieve captions similar to it from a replaceable datastore, which are then used to construct a prompt. Next, we feed this prompt to a GPT-2 decoder and introduce cross-attention layers between the CLAP encoder and GPT-2 to condition the audio for caption generation. Experiments on two benchmark datasets, Clotho and AudioCaps, show that RECAP achieves competitive performance in in-domain settings and significant improvements in out-of-domain settings. Additionally, due to its capability to exploit a large text-captions-only datastore in a training-free fashion, RECAP shows unique capabilities of captioning novel audio events never seen during training and compositional audios with multiple events. To promote research in this space, we also release 150,000+ new weakly labeled captions for AudioSet, AudioCaps, and Clotho1.

Self-supervised learning with a contrastive batch approach has become a powerful tool for representation learning in computer vision. The performance of downstream tasks is proportional to the quality of visual features learned while self-supervised pre-training. The existing contrastive batch approaches heavily depend on data augmentation to learn latent information from unlabelled datasets. We argue that introducing the dataset’s intra-class variation in a contrastive batch approach improves visual representation quality further. In this paper, we propose a novel self-supervised learning approach named Iterative Pseudo-supervised Contrastive Learning (IPCL), which utilizes a balanced combination of image augmentations and pseudo-class information to improve the visual representation iteratively. Experimental results illustrate that our proposed method surpasses the baseline self-supervised method with the batch contrastive approach. It improves the visual representation quality over multiple datasets, leading to better performance on the downstream unsupervised image classification task. Code is available at https://github.com/SonalKumar95/IPCL.

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved performance in many downstream applications, including zero-shot audio classification, audio retrieval, etc. However, the ability of these models to effectively perform compositional reasoning remains largely unexplored and necessitates additional research. In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-world audio samples, to evaluate compositional reasoning in ALMs. Our proposed CompA-order evaluates how well an ALM understands the order or occurrence of acoustic events in audio, and CompA-attribute evaluates attribute-binding of acoustic events. An instance from either benchmark consists of two audio-caption pairs, where both audios have the same acoustic events but with different compositions. An ALM is evaluated on how well it matches the right audio to the right caption. Using this benchmark, we first show that current ALMs perform only marginally better than random chance, thereby struggling with compositional reasoning. Next, we propose CompA-CLAP, where we fine-tune CLAP using a novel learning method to improve its compositional reasoning abilities. To train CompA-CLAP, we first propose improvements to contrastive training with composition-aware hard negatives, allowing for more focused training. Next, we propose a novel modular contrastive loss that helps the model learn fine-grained compositional understanding and overcomes the acute scarcity of openly available compositional audios. CompA-CLAP significantly improves over all our baseline models on the CompA benchmark, indicating its superior compositional reasoning capabilities.

Instruction Tuning (IT), the process of training large language models (LLMs) using instruction-response pairs, has emerged as the predominant method for transforming base pre-trained LLMs into open-domain conversational agents. While IT has achieved notable success and widespread adoption, its limitations and shortcomings remain underexplored. In this paper, through rigorous experiments and an in-depth analysis of the changes LLMs undergo through IT, we reveal various limitations of IT. In particular, we show that (1) IT fails to enhance knowledge or skills in LLMs. LoRA fine-tuning is limited to learning response initiation and style tokens, and full-parameter fine-tuning leads to knowledge degradation. (2) Copying response patterns from IT datasets derived from knowledgeable sources leads to a decline in response quality. (3) Full-parameter fine-tuning increases hallucination by inaccurately borrowing tokens from conceptually similar instances in the IT dataset for generating responses. (4) Popular methods to improve IT do not lead to performance improvements over a simple LoRA fine-tuned model. Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets. We hope the insights and challenges revealed in this paper inspire future work in related directions.

Sreyan Ghosh, Utkarsh Tyagi, Manan Suri, Sonal Kumar, Ramaneswaran S, Dinesh Manocha. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, S Ramaneswaran, S Sakshi, Utkarsh Tyagi, Dinesh Manocha. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

The tremendous growth of social media users interacting in online conversations has led to significant growth in hate speech affecting people from various demographics.Most of the prior works focus on detecting explicit hate speech, which is overt and leverages hateful phrases, with very little work focusing on detecting hate speech that is implicit or denotes hatred through indirect or coded language.In this paper, we present CoSyn, a context synergized neural network that explicitly incorporates user-and conversational-context for detecting implicit hate speech in online conversations.CoSyn introduces novel ways to encode these external contexts and employs a novel context interaction mechanism that clearly captures the interplay between them, making independent assessments of the amounts of information to be retrieved from these noisy contexts.Additionally, it carries out all these operations in the hyperbolic space to account for the scalefree dynamics of social media.We demonstrate the effectiveness of CoSyn on 6 hate speech datasets and show that CoSyn outperforms all our baselines in detecting implicit hate speech with absolute improvements in the range of 1.24% -57.8%.We make our code available 1 .

Biomedical Named Entity Recognition (BioNER) is the fundamental task of identifying named entities from biomedical text. However, BioNER suffers from severe data scarcity and lacks high-quality labeled data due to the highly specialized and expert knowledge required for annotation. Though data augmentation has shown to be highly effective for low-resource NER in general, existing data augmentation techniques fail to produce factual and diverse augmentations for BioNER. In this paper, we present BioAug, a novel data augmentation framework for low-resource BioNER. BioAug, built on BART, is trained to solve a novel text reconstruction task based on selective masking and knowledge augmentation. Post training, we perform conditional generation and generate diverse augmentations conditioning BioAug on selectively corrupted text similar to the training stage. We demonstrate the effectiveness of BioAug on 5 benchmark BioNER datasets and show that BioAug outperforms all our baselines by a significant margin (1.5%-21.5% absolute improvement) and is able to generate augmentations that are both more factual and diverse. Code: https://github.com/Sreyan88/BioAug.

Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text.Moreover, most works focus on leveraging only contextual information captured by the linear sequences in text, thus ignoring the structured information in text which is efficiently captured by dependency trees.In this paper, building on the span classification paradigm of entity recognition, we propose a novel architecture for detecting disfluencies in transcripts from spoken utterances, incorporating both contextual information through transformers and long-distance structured information captured by dependency trees, through graph convolutional networks (GCNs).Experimental results show that our proposed model achieves state-of-the-art results on the widely used English Switchboard for disfluency detection and outperforms prior-art by a significant margin.We make all our codes publicly available on GitHub 1 .