Related papers: Interpretable Audio Editing Evaluation via Chain-o…

Emotion recognition from speech is a challenging task that requires capturing both linguistic and paralinguistic cues, with critical applications in human-computer interaction and mental health monitoring. Recent works have highlighted the…

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable…

The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context. Traditional methods often depend on human…

Recently, Multimodal Large Language Models (MLLMs) have achieved exceptional performance across diverse tasks, continually surpassing previous expectations regarding their capabilities. Nevertheless, their proficiency in perceiving emotions…

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain…

Developers of text-to-speech synthesizers (TTS) often make use of human raters to assess the quality of synthesized speech. We demonstrate that we can model human raters' mean opinion scores (MOS) of synthesized speech using a deep…

Speech Emotion Recognition (SER) is typically trained and evaluated on majority-voted labels, which simplifies benchmarking but masks subjectivity and provides little transparency into why predictions are made. This neglects valid minority…

Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important to human perception and intent. Such metrics frequently…

Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the…

Multimodal language analysis is a rapidly evolving field that leverages multiple modalities to enhance the understanding of high-level semantics underlying human conversational utterances. Despite its significance, little research has…

In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, they often correlate poorly with perceptual quality and…

Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.g., mood, location, or social setting). In this paper, we introduce a Large Language Model…

Multimodal sentiment analysis is an important area for understanding the user's internal states. Deep learning methods were effective, but the problem of poor interpretability has gradually gained attention. Previous works have attempted to…

Fine-grained opinion analysis of text provides a detailed understanding of expressed sentiments, including the addressed entity. Although this level of detail is valuable, annotating opinions in datasets for model training requires…

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically…

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

Machine learning (ML) models have been applied to a wide range of natural language processing (NLP) tasks in recent years. In addition to making accurate decisions, the necessity of understanding how models make their decisions has become…

Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to…

We investigate whether large language models (LLMs) can generate effective, user-facing explanations from a mathematically interpretable recommendation model. The model is based on constrained matrix factorization, where user types are…