MACE: Leveraging Audio for Evaluating Audio Captioning Systems

The Automated Audio Captioning (AAC) task aims to describe an audio signal using natural language. To evaluate machine-generated captions, the metrics should take into account audio events, acoustic scenes, paralinguistics, signal characteristics, and other audio information. Traditional AAC evaluation relies on natural language generation metrics like ROUGE and BLEU, image captioning metrics such as SPICE and CIDEr, or Sentence-BERT embedding similarity. However, these metrics only compare generated captions to human references, overlooking the audio signal itself. In this work, we propose MACE (Multimodal Audio-Caption Evaluation), a novel metric that integrates both audio and reference captions for comprehensive audio caption evaluation. MACE incorporates audio information from audio as well as predicted and reference captions and weights it with a fluency penalty. Our experiments demonstrate MACE's superior performance in predicting human quality judgments compared to traditional metrics. Specifically, MACE achieves a 3.28% and 4.36% relative accuracy improvement over the FENSE metric on the AudioCaps-Eval and Clotho-Eval datasets respectively. Moreover, it significantly outperforms all the previous metrics on the audio captioning evaluation task. The metric is opensourced at https://github.com/satvik-dixit/mace

FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content Analysis

The proliferation of tobacco-related content on social media platforms poses significant challenges for public health monitoring and intervention. This paper introduces a novel multi-modal deep learning framework named Flow-Attention Adaptive Semantic Hierarchical Fusion (FLAASH) designed to analyze tobacco-related video content comprehensively. FLAASH addresses the complexities of integrating visual and textual information in short-form videos by leveraging a hierarchical fusion mechanism inspired by flow network theory. Our approach incorporates three key innovations, including a flow-attention mechanism that captures nuanced interactions between visual and textual modalities, an adaptive weighting scheme that balances the contribution of different hierarchical levels, and a gating mechanism that selectively emphasizes relevant features. This multi-faceted approach enables FLAASH to effectively process and analyze diverse tobacco-related content, from product showcases to usage scenarios. We evaluate FLAASH on the Multimodal Tobacco Content Analysis Dataset (MTCAD), a large-scale collection of tobacco-related videos from popular social media platforms. Our results demonstrate significant improvements over existing methods, outperforming state-of-the-art approaches in classification accuracy, F1 score, and temporal consistency. The proposed method also shows strong generalization capabilities when tested on standard video question-answering datasets, surpassing current models. This work contributes to the intersection of public health and artificial intelligence, offering an effective tool for analyzing tobacco promotion in digital media.

On the Diversity of Synthetic Data and its Impact on Training Large Language Models

The rise of Large Language Models (LLMs) has accentuated the need for diverse, high-quality pre-training data. Synthetic data emerges as a viable solution to the challenges of data scarcity and inaccessibility. While previous literature has focused predominantly on the quality and quantity of real data, our work enables the measurement of diversity in synthetic data and explores its impact on LLM performance. We study the downstream effects of synthetic data diversity during both the pre-training and fine-tuning stages by introducing a new diversity metric, \textit{LLM cluster-agent}, designed to evaluate the diversity of synthetic datasets. Through a series of controlled experiments with models of 350M and 1.4B parameters, we demonstrate that the proposed cluster-based LLM scoring of diversity correlates positively with both pre-training and supervised fine-tuning performance. Our findings also reveal that synthetic data diversity in pre-training affects supervised fine-tuning more significantly than pre-training itself, even for smaller models. We hope this study advances our understanding of the optimal use of synthetic data in LLM training and opens new avenues for efficient data generation processes.

What Do Speech Foundation Models Not Learn About Speech?

Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec, HuBERT, and Qwen2-Audio focusing on their learned representations in both paralinguistic and non-paralinguistic tasks from the Dynamic-SUPERB benchmark. Our study addresses three key questions: (1) What non-verbal cues (e.g., speaker intent, emotion, environmental context) are captured? (2) How are these cues represented across different layers of the models? and (3) To what extent can these representations be effectively adapted to downstream tasks? To answer these questions, we first evaluate the models in a zero-shot setting, followed by fine-tuning on layer-wise features extracted from these models. Our results provide insights into the models' capacity for generalization, the characteristics of their layer-wise representations, and the degree of transformation required for downstream task adaptation. Our findings suggest that some of these models perform well on various tasks in zero-shot settings, despite not being explicitly trained for those tasks. We also observe that zero-shot performance correlates with better-learned representations. The analysis of layer-wise features demonstrates that some models exhibit a convex relationship between the separability of the learned representations and model depth, with different layers capturing task-specific features.

RelUNet: Relative Channel Fusion U-Net for Multichannel Speech Enhancement

Neural multi-channel speech enhancement models, in particular those based on the U-Net architecture, demonstrate promising performance and generalization potential. These models typically encode input channels independently, and integrate the channels during later stages of the network. In this paper, we propose a novel modification of these models by incorporating relative information from the outset, where each channel is processed in conjunction with a reference channel through stacking. This input strategy exploits comparative differences to adaptively fuse information between channels, thereby capturing crucial spatial information and enhancing the overall performance. The experiments conducted on the CHiME-3 dataset demonstrate improvements in speech enhancement metrics across various architectures.

Improving Speaker Representations Using Contrastive Losses on Multi-scale Features

Speaker verification systems have seen significant advancements with the introduction of Multi-scale Feature Aggregation (MFA) architectures, such as MFA-Conformer and ECAPA-TDNN. These models leverage information from various network depths by concatenating intermediate feature maps before the pooling and projection layers, demonstrating that even shallower feature maps encode valuable speaker-specific information. Building upon this foundation, we propose a Multi-scale Feature Contrastive (MFCon) loss that directly enhances the quality of these intermediate representations. Our MFCon loss applies contrastive learning to all feature maps within the network, encouraging the model to learn more discriminative representations at the intermediate stage itself. By enforcing better feature map learning, we show that the resulting speaker embeddings exhibit increased discriminative power. Our method achieves a 9.05% improvement in equal error rate (EER) compared to the standard MFA-Conformer on the VoxCeleb-1O test set.

Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection

We introduce a novel, general-purpose audio generation framework specifically designed for anomaly detection and localization. Unlike existing datasets that predominantly focus on industrial and machine-related sounds, our framework focuses a broader range of environments, particularly useful in real-world scenarios where only audio data are available, such as in video-derived or telephonic audio. To generate such data, we propose a new method inspired by the LLM-Modulo framework, which leverages large language models(LLMs) as world models to simulate such real-world scenarios. This tool is modular allowing a plug-and-play approach. It operates by first using LLMs to predict plausible real-world scenarios. An LLM further extracts the constituent sounds, the order and the way in which these should be merged to create coherent wholes. Much like the LLM-Modulo framework, we include rigorous verification of each output stage, ensuring the reliability of the generated data. The data produced using the framework serves as a benchmark for anomaly detection applications, potentially enhancing the performance of models trained on audio data, particularly in handling out-of-distribution cases. Our contributions thus fill a critical void in audio anomaly detection resources and provide a scalable tool for generating diverse, realistic audio data.

ImageFolder: Autoregressive Image Generation with Folded Tokens

Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the image reconstruction quality. However, tokenizers with longer token lengths are not guaranteed to achieve better generation quality. There exists a trade-off between reconstruction and generation quality regarding token length. In this paper, we investigate the impact of token length on both image reconstruction and generation and provide a flexible solution to the tradeoff. We propose ImageFolder, a semantic tokenizer that provides spatially aligned image tokens that can be folded during autoregressive modeling to improve both generation efficiency and quality. To enhance the representative capability without increasing token length, we leverage dual-branch product quantization to capture different contexts of images. Specifically, semantic regularization is introduced in one branch to encourage compacted semantic information while another branch is designed to capture the remaining pixel-level details. Extensive experiments demonstrate the superior quality of image generation and shorter token length with ImageFolder tokenizer.

ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech

Neural codecs have become crucial to recent speech and audio generation research. In addition to signal compression capabilities, discrete codecs have also been found to enhance downstream training efficiency and compatibility with autoregressive language models. However, as extensive downstream applications are investigated, challenges have arisen in ensuring fair comparisons across diverse applications. To address these issues, we present a new open-source platform ESPnet-Codec, which is built on ESPnet and focuses on neural codec training and evaluation. ESPnet-Codec offers various recipes in audio, music, and speech for training and evaluation using several widely adopted codec models. Together with ESPnet-Codec, we present VERSA, a standalone evaluation toolkit, which provides a comprehensive evaluation of codec performance over 20 audio evaluation metrics. Notably, we demonstrate that ESPnet-Codec can be integrated into six ESPnet tasks, supporting diverse applications.

Revisiting Acoustic Features for Robust ASR

Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, special effects as well as attacks by malicious actors (adversarial attacks). Recent works seek to improve accuracy and robustness by developing novel Deep Neural Networks (DNNs) and curating diverse training datasets for them, while using relatively simple acoustic features. While this approach improves robustness to the types of noise present in the training data, it confers limited robustness against unseen noises and negligible robustness to adversarial attacks. In this paper, we revisit the approach of earlier works that developed acoustic features inspired by biological auditory perception that could be used to perform accurate and robust ASR. In contrast, Specifically, we evaluate the ASR accuracy and robustness of several biologically inspired acoustic features. In addition to several features from prior works, such as gammatone filterbank features (GammSpec), we also propose two new acoustic features called frequency masked spectrogram (FreqMask) and difference of gammatones spectrogram (DoGSpec) to simulate the neuro-psychological phenomena of frequency masking and lateral suppression. Experiments on diverse models and datasets show that (1) DoGSpec achieves significantly better robustness than the highly popular log mel spectrogram (LogMelSpec) with minimal accuracy degradation, and (2) GammSpec achieves better accuracy and robustness to non-adversarial noises from the Speech Robust Bench benchmark, but it is outperformed by DoGSpec against adversarial attacks.