Related papers: Enhancing Automated Audio Captioning via Large Lan…
Current speech evaluation suffers from two critical limitations: the need and difficulty of designing specialized systems targeting individual audio characteristics, and poor correlation between automatic evaluation methods and human…
Music captioning, or the task of generating a natural language description of music, is useful for both music understanding and controllable music generation. Training captioning models, however, typically requires high-quality music…
Image Captioning, or the automatic generation of descriptions for images, is one of the core problems in Computer Vision and has seen considerable progress using Deep Learning Techniques. We propose to use Inception-ResNet Convolutional…
Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single…
Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based…
Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model…
In this paper, we propose a submission to the x-to-audio alignment (XACLE) challenge. The goal is to predict semantic alignment of a given general audio and text pair. The proposed system is based on a large audio language model (LALM)…
Speech Emotion Captioning (SEC) has gradually become an active research task. The emotional content conveyed through human speech are often complex, and classifying them into fixed categories may not be enough to fully capture speech…
Audio captioning is a recently proposed task for automatically generating a textual description of a given audio clip. In this study, a novel deep network architecture with audio embeddings is presented to predict audio captions. Within the…
In this paper we present our researches regarding automat parsing of audio recordings. These recordings are obtained from children with dyslalia and are necessary for an accurate identification of speech problems. We develop the ADM…
Automated audio captioning is a cross-modal translation task for describing the content of audio clips with natural language sentences. This task has attracted increasing attention and substantial progress has been made in recent years.…
Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction. This mismatch injects acoustically driven uncertainty into the discrete…
Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…
Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance,…
Large Audio Language Models (LALMs) have emerged as powerful tools for speech-related tasks but remain underexplored for fine-tuning, especially with limited speech data. To bridge this gap, we systematically examine how different…
Most end-to-end (E2E) speech recognition models are composed of encoder and decoder blocks that perform acoustic and language modeling functions. Pretrained large language models (LLMs) have the potential to improve the performance of E2E…
Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation…
Large audio language models (ALMs) extend LLMs with auditory understanding. A common approach freezes the LLM and trains only an adapter on self-generated targets. However, this fails for reasoning LLMs (RLMs) whose built-in…
Video-text retrieval has been stuck in the information mismatch caused by personalized and inadequate textual descriptions of videos. The substantial information gap between the two modalities hinders an effective cross-modal representation…
Generating audio captions is a new research area that combines audio and natural language processing to create meaningful textual descriptions for audio clips. To address this problem, previous studies mostly use the encoder-decoder based…