Related papers: Please Make it Sound like Human: Encoder-Decoder v…

This study explores how discussing metaphors for AI can help build awareness of the frames that shape our understanding of AI systems, particularly large language models (LLMs) like ChatGPT. Given the pressing need to teach "critical AI…

Generative AI offers a simple, prompt-based alternative to fine-tuning smaller BERT-style LLMs for text classification tasks. This promises to eliminate the need for manually labeled training data and task-specific model training. However,…

Despite recent achievements of deep learning automatic music generation algorithms, few approaches have been proposed to evaluate whether a single-track music excerpt is composed by automatons or Homo sapiens. To tackle this problem, we…

Traditional medical basic sciences educational approaches follow a one-size-fits-all model, neglecting the diverse learning styles of individual students. I propose an intelligent AI companion which will fill this gap by providing…

By using a trigram model and fine-tuning a pretrained BERT model for sequence classification, we show that machine translation and human translation can be classified with an accuracy above chance level, which suggests that machine…

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other…

While recent advancements in commercial large language models (LM) have shown promising results in medical tasks, their closed-source nature poses significant privacy and security concerns, hindering their widespread use in the medical…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

Collecting large, aligned cross-modal datasets for music-flavor research is difficult because perceptual experiments are costly and small by design. We address this bottleneck through two complementary experiments. The first tests whether…

This paper presents an effective approach to detect AI-generated text, developed for the Defactify 4.0 shared task at the fourth workshop on multimodal fact checking and hate speech detection. The task consists of two subtasks: Task-A,…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

Interpretability of machine learning models has gained more and more attention among researchers in the artificial intelligence (AI) and human-computer interaction (HCI) communities. Most existing work focuses on decision making, whereas we…

The rapid proliferation of Large Language Models has significantly increased the difficulty of distinguishing between human-written and AI generated texts, raising critical issues across academic, editorial, and social domains. This paper…

Music Information Retrieval (MIR) systems are highly vulnerable to adversarial attacks that are often imperceptible to humans, primarily due to a misalignment between model feature spaces and human auditory perception. Existing defenses and…

Automated coaching messages for weight control can save time and costs, but their repetitive, generic nature may limit their effectiveness compared to human coaching. Large language model (LLM) based artificial intelligence (AI) chatbots,…

Codec-based text-to-speech (TTS) models have shown impressive quality with zero-shot voice cloning abilities. However, they often struggle with more expressive references or complex text inputs. We present MARS6, a robust encoder-decoder…

Punctuation and Segmentation are key to readability in Automatic Speech Recognition (ASR), often evaluated using F1 scores that require high-quality human transcripts and do not reflect readability well. Human evaluation is expensive,…

As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount. However, AI is currently facing a reproducibility crisis driven…

ChatGPT, GPT-3.5, and other large language models (LLMs) have drawn significant attention since their release, and the abilities of these models have been investigated for a wide variety of tasks. In this research we investigate to what…