相关论文: Synthio: Augmenting Small-Scale Audio Classificati…

End-to-end Speech Translation is hindered by a lack of available data resources. While most of them are based on documents, a sentence-level version is available, which is however single and static, potentially impeding the usefulness of…

Although automatic pathological speech detection approaches show promising results when clean recordings are available, they are vulnerable to additive noise. Recently it has been shown that databases commonly used to develop and evaluate…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of…

Automated audio captioning is multi-modal translation task that aim to generate textual descriptions for a given audio clip. In this paper we propose a full Transformer architecture that utilizes Patchout as proposed in [1], significantly…

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings…

This paper introduces Synthetic Enclosed Echoes (SEE), a novel dataset designed to enhance robot perception and 3D reconstruction capabilities in underwater environments. SEE comprises high-fidelity synthetic sonar data, complemented by a…

Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevalent. However, the quality and utility of augmented data…

The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Synthetic data generation offers a promising alternative;…

Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation,…

In this paper, we introduce ConversaSynth, a framework designed to generate synthetic conversation audio using large language models (LLMs) with multiple persona settings. The framework first creates diverse and coherent text-based…

Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have not…

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

This letter presents an incremental text-to-speech (TTS) method that performs synthesis in small linguistic units while maintaining the naturalness of output speech. Incremental TTS is generally subject to a trade-off between latency and…

The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what extent can low error rates on academic benchmarks translate…

With the development of large-scale diffusion-based and language-modeling-based generative models, impressive progress has been achieved in text-to-audio generation. Despite producing high-quality outputs, existing text-to-audio models…

We introduce EzAudio, a text-to-audio (T2A) generation framework designed to produce high-quality, natural-sounding sound effects. Core designs include: (1) We propose EzAudio-DiT, an optimized Diffusion Transformer (DiT) designed for audio…

End-to-end automatic speech recognition often degrades on domain-specific data due to scarce in-domain resources. We propose a synthetic-data-based domain adaptation framework with two contributions: (1) a large language model (LLM)-based…

Healthcare research and development face significant obstacles due to data scarcity and stringent privacy regulations, such as HIPAA and the GDPR, restricting access to essential real-world medical data. These limitations impede innovation,…

This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques.…