Search

Speech forensic tasks (SFTs), such as automatic speaker recognition (ASR), speech emotion recognition (SER), gender recognition (GR), and age estimation (AE), find use in different security and biometric applications. Previous works have applied various techniques, with recent studies focusing on applying speech foundation models (SFMs) for improved performance. However, most prior efforts have centered on building individual models for each task separately, despite the inherent similarities among these tasks. This isolated approach results in higher computational resource requirements, increased costs, time consumption, and maintenance challenges. In this study, we address these challenges by employing a multi-task learning strategy. Firstly, we explore the various state-of-the-art (SOTA) SFMs by extracting their representations for learning these SFTs and investigating their effectiveness at each task specifically. Secondly, we analyze the performance of the extracted representations on the SFTs in a multi-task learning framework. We observe a decline in performance when SFTs are modeled together compared to individual task-specific models, and as a remedy, we propose multi-view learning (MVL). Views are representations from different SFMs transformed into distinct abstract spaces by characteristics unique to each SFM. By leveraging MVL, we integrate these diverse representations to capture complementary information across tasks, enhancing the shared learning process. We introduce a new framework called TANGO (Task Alignment with iNter-view Gated Optimal transport) to implement this approach. With TANGO, we achieve the topmost performance in comparison to individual SFM representations as well as baseline fusion techniques across benchmark datasets such as CREMA-D, emo-DB, and BAVED.

Despite being trained exclusively on speech data, speech foundation models (SFMs) like Whisper have shown impressive performance in non-speech tasks such as audio classification. This is partly because speech shares some common traits with audio, enabling SFMs to transfer effectively. In this study, we push the boundaries by evaluating SFMs on a more challenging out-of-domain (OOD) task: classifying physiological time-series signals. We test two key hypotheses: first, that SFMs can generalize to physiological signals by capturing shared temporal patterns; second, that multilingual SFMs will outperform others due to their exposure to greater variability during pre-training, leading to more robust, generalized representations. Our experiments, conducted for stress recognition using ECG (Electrocardiogram), EMG (Electromyography), and EDA (Electrodermal Activity) signals, reveal that models trained on SFM-derived representations outperform those trained on raw physiological signals. Among all models, multilingual SFMs achieve the highest accuracy, supporting our hypothesis and demonstrating their OOD capabilities. This work positions SFMs as promising tools for new uncharted domains beyond speech.

In this work, we introduce SeQuiFi, a novel approach for mitigating catastrophic forgetting (CF) in speech emotion recognition (SER). SeQuiFi adopts a sequential class-finetuning strategy, where the model is fine-tuned incrementally on one emotion class at a time, preserving and enhancing retention for each class. While various state-of-the-art (SOTA) methods, such as regularization-based, memory-based, and weight-averaging techniques, have been proposed to address CF, it still remains a challenge, particularly with diverse and multilingual datasets. Through extensive experiments, we demonstrate that SeQuiFi significantly outperforms both vanilla fine-tuning and SOTA continual learning techniques in terms of accuracy and F1 scores on multiple benchmark SER datasets, including CREMA-D, RAVDESS, Emo-DB, MESD, and SHEMO, covering different languages.

The adaptation of foundation models has significantly advanced environmental audio deepfake detection (EADD), a rapidly growing area of research. These models are typically fine-tuned or utilized in their frozen states for downstream tasks. However, the dimensionality of their representations can substantially lead to a high parameter count of downstream models, leading to higher computational demands. So, a general way is to compress these representations by leveraging state-of-the-art (SOTA) unsupervised dimensionality reduction techniques (PCA, SVD, KPCA, GRP) for efficient EADD. However, with the application of such techniques, we observe a drop in performance. So in this paper, we show that representation vectors contain redundant information, and randomly selecting 40-50% of representation values and building downstream models on it preserves or sometimes even improves performance. We show that such random selection preserves more performance than the SOTA dimensionality reduction techniques while reducing model parameters and inference time by almost over half., Comment: Submitted to ICASSP 2025

In this study, we address the challenge of depression detection from speech, focusing on the potential of non-semantic features (NSFs) to capture subtle markers of depression. While prior research has leveraged various features for this task, NSFs-extracted from pre-trained models (PTMs) designed for non-semantic tasks such as paralinguistic speech processing (TRILLsson), speaker recognition (x-vector), and emotion recognition (emoHuBERT)-have shown significant promise. However, the potential of combining these diverse features has not been fully explored. In this work, we demonstrate that the amalgamation of NSFs results in complementary behavior, leading to enhanced depression detection performance. Furthermore, to our end, we introduce a simple novel framework, FuSeR, designed to effectively combine these features. Our results show that FuSeR outperforms models utilizing individual NSFs as well as baseline fusion techniques and obtains state-of-the-art (SOTA) performance in E-DAIC benchmark with RMSE of 5.51 and MAE of 4.48, establishing it as a robust approach for depression detection., Comment: Submitted to ICASSP 2025

In this study, we investigate multimodal foundation models (MFMs) for emotion recognition from non-verbal sounds. We hypothesize that MFMs, with their joint pre-training across multiple modalities, will be more effective in non-verbal sounds emotion recognition (NVER) by better interpreting and differentiating subtle emotional cues that may be ambiguous in audio-only foundation models (AFMs). To validate our hypothesis, we extract representations from state-of-the-art (SOTA) MFMs and AFMs and evaluated them on benchmark NVER datasets. We also investigate the potential of combining selected foundation model representations to enhance NVER further inspired by research in speech recognition and audio deepfake detection. To achieve this, we propose a framework called MATA (Intra-Modality Alignment through Transport Attention). Through MATA coupled with the combination of MFMs: LanguageBind and ImageBind, we report the topmost performance with accuracies of 76.47%, 77.40%, 75.12% and F1-scores of 70.35%, 76.19%, 74.63% for ASVP-ESD, JNV, and VIVAE datasets against individual FMs and baseline fusion techniques and report SOTA on the benchmark datasets., Comment: Submitted to ICASSP 2025

In this study, for the first time, we extensively investigate whether music foundation models (MFMs) or speech foundation models (SFMs) work better for singing voice deepfake detection (SVDD), which has recently attracted attention in the research community. For this, we perform a comprehensive comparative study of state-of-the-art (SOTA) MFMs (MERT variants and music2vec) and SFMs (pre-trained for general speech representation learning as well as speaker recognition). We show that speaker recognition SFM representations perform the best amongst all the foundation models (FMs), and this performance can be attributed to its higher efficacy in capturing the pitch, tone, intensity, etc, characteristics present in singing voices. To our end, we also explore the fusion of FMs for exploiting their complementary behavior for improved SVDD, and we propose a novel framework, FIONA for the same. With FIONA, through the synchronization of x-vector (speaker recognition SFM) and MERT-v1-330M (MFM), we report the best performance with the lowest Equal Error Rate (EER) of 13.74 %, beating all the individual FMs as well as baseline FM fusions and achieving SOTA results., Comment: Submitted to ICASSP 2025

In this paper, we work towards extending Audio-Visual Question Answering (AVQA) to multilingual settings. Existing AVQA research has predominantly revolved around English and replicating it for addressing AVQA in other languages requires a substantial allocation of resources. As a scalable solution, we leverage machine translation and present two multilingual AVQA datasets for eight languages created from existing benchmark AVQA datasets. This prevents extra human annotation efforts of collecting questions and answers manually. To this end, we propose, MERA framework, by leveraging state-of-the-art (SOTA) video, audio, and textual foundation models for AVQA in multiple languages. We introduce a suite of models namely MERA-L, MERA-C, MERA-T with varied model architectures to benchmark the proposed datasets. We believe our work will open new research directions and act as a reference benchmark for future works in multilingual AVQA., Comment: Accepted to Interspeech 2024

Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we introduce FastAST, a framework that integrates Token Merging (ToMe) into the AST framework. FastAST enhances inference speed without requiring extensive retraining by merging similar tokens in audio spectrograms. Furthermore, during training, FastAST brings about significant speed improvements. The experiments indicate that FastAST can increase audio classification throughput with minimal impact on accuracy. To mitigate the accuracy impact, we integrate Cross-Model Knowledge Distillation (CMKD) into the FastAST framework. Integrating ToMe and CMKD into AST results in improved accuracy compared to AST while maintaining faster inference speeds. FastAST represents a step towards real-time, resource-efficient audio analysis., Comment: Accepted to Interspeech 2024

Spectral clustering methods have gained widespread recognition for their effectiveness in clustering high-dimensional data. Among these techniques, constrained spectral clustering has emerged as a prominent approach, demonstrating enhanced performance by integrating pairwise constraints. However, the application of such constraints to semidefinite spectral clustering, a variant that leverages semidefinite programming to optimize clustering objectives, remains largely unexplored. In this paper, we introduce a novel framework for seamlessly integrating pairwise constraints into semidefinite spectral clustering. Our methodology systematically extends the capabilities of semidefinite spectral clustering to capture complex data structures, thereby addressing real-world clustering challenges more effectively. Additionally, we extend this framework to encompass both active and self-taught learning scenarios, further enhancing its versatility and applicability. Empirical studies conducted on well-known datasets demonstrate the superiority of our proposed framework over existing spectral clustering methods, showcasing its robustness and scalability across diverse datasets and learning settings. By bridging the gap between constrained learning and semidefinite spectral clustering, our work contributes to the advancement of spectral clustering techniques, offering researchers and practitioners a versatile tool for addressing complex clustering challenges in various real-world applications. Access to the data, code, and experimental results is provided for further exploration (https://github.com/swarupbehera/SCCCS).

Sports visualization focuses on the use of structured data, such as box-score data and tracking data. Unstructured data sources pertaining to sports are available in various places such as blogs, social media posts, and online news articles. Sports visualization methods either not fully exploited the information present in these sources or the proposed visualizations through the use of these sources did not augment to the body of sports visualization methods. We propose the use of unstructured data, namely cricket short text commentary for visualization. The short text commentary data is used for constructing individual player's strength rules and weakness rules. A computationally feasible definition for player's strength rule and weakness rule is proposed. A visualization method for the constructed rules is presented. In addition, players having similar strength rules or weakness rules is computed and visualized. We demonstrate the usefulness of short text commentary in visualization by analyzing the strengths and weaknesses of cricket players using more than one million text commentaries. We validate the constructed rules through two validation methods. The collected data, source code, and obtained results on more than 500 players are made publicly available.

Audio Question Answering (AQA) constitutes a pivotal task in which machines analyze both audio signals and natural language questions to produce precise natural language answers. The significance of possessing high-quality, diverse, and extensive AQA datasets cannot be overstated when aiming for the precision of an AQA system. While there has been notable focus on developing accurate and efficient AQA models, the creation of high-quality, diverse, and extensive datasets for the specific task at hand has not garnered considerable attention. To address this challenge, this work makes several contributions. We introduce a scalable AQA data generation pipeline, denoted as the AQUALLM framework, which relies on Large Language Models (LLMs). This framework utilizes existing audio-caption annotations and incorporates state-of-the-art LLMs to generate expansive, high-quality AQA datasets. Additionally, we present three extensive and high-quality benchmark datasets for AQA, contributing significantly to the progression of AQA research. AQA models trained on the proposed datasets set superior benchmarks compared to the existing state-of-the-art. Moreover, models trained on our datasets demonstrate enhanced generalizability when compared to models trained using human-annotated AQA data. Code and datasets will be accessible on GitHub~\footnote{\url{https://github.com/swarupbehera/AQUALLM}}.

Devising player-specific strategies in cricket necessitates a meticulous understanding of each player's unique strengths and weaknesses. Nevertheless, the absence of a definitive computational approach to extract such insights from cricket players poses a significant challenge. This paper seeks to address this gap by establishing computational models designed to extract the rules governing player strengths and weaknesses, thereby facilitating the development of tailored strategies for individual players. The complexity of this endeavor lies in several key areas: the selection of a suitable dataset, the precise definition of strength and weakness rules, the identification of an appropriate learning algorithm, and the validation of the derived rules. To tackle these challenges, we propose the utilization of unstructured data, specifically cricket text commentary, as a valuable resource for constructing comprehensive strength and weakness rules for cricket players. We also introduce computationally feasible definitions for the construction of these rules, and present a dimensionality reduction technique for the rule-building process. In order to showcase the practicality of this approach, we conduct an in-depth analysis of cricket player strengths and weaknesses using a vast corpus of more than one million text commentaries. Furthermore, we validate the constructed rules through two distinct methodologies: intrinsic and extrinsic. The outcomes of this research are made openly accessible, including the collected data, source code, and results for over 250 cricket players, which can be accessed at https://bit.ly/2PKuzx8., Comment: The initial work was published in the ICMLA 2019 conference