相关论文: Synthetic training set generation using text-to-au…

Industry datasets used for text classification are rarely created for that purpose. In most cases, the data and target predictions are a by-product of accumulated historical data, typically fraught with noise, present in both the text-based…

Emotional text-to-speech synthesis (ETTS) has seen much progress in recent years. However, the generated voice is often not perceptually identifiable by its intended emotion category. To address this problem, we propose a new interactive…

Recent advancements in foundation models have sparked interest in respiratory audio foundation models. However, the effectiveness of applying conventional pre-training schemes to datasets that are small-sized and lack diversity has not been…

The field of audio captioning has seen significant advancements in recent years, driven by the availability of large-scale audio datasets and advancements in deep learning techniques. In this technical report, we present our approach to…

Generative models have been showing potential for producing data in mass. This study explores the enhancement of clinical natural language processing performance by utilizing synthetic data generated from advanced language models. Promising…

The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not…

Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However, the evaluation of neural IR has so far been limited to…

Recent trends in neural network based text-to-speech/speech synthesis pipelines have employed recurrent Seq2seq architectures that can synthesize realistic sounding speech directly from text characters. These systems however have complex…

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

Deep neural networks have recently achieved breakthroughs in sound generation. Despite the outstanding sample quality, current sound generation models face issues on small-scale datasets (e.g., overfitting), significantly limiting…

The increasing use of machine learning models has amplified the demand for high-quality, large-scale multimodal datasets. However, the availability of such datasets, especially those combining acoustic, visual and textual data, remains…

Accurately evaluating model performance is crucial for deploying machine learning systems in real-world applications. Traditional methods often require a sufficiently large labeled test set to ensure a reliable evaluation. However, in many…

We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy…

The objective of this paper is an automatic Audio Description (AD) model that ingests movies and outputs AD in text form. Generating high-quality movie AD is challenging due to the dependency of the descriptions on context, and the limited…

Recent breakthroughs in synthetic data generation approaches made it possible to produce highly photorealistic images which are hardly distinguishable from real ones. Furthermore, synthetic generation pipelines have the potential to…

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain…

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…

Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…

Passive Acoustic Monitoring (PAM) analysis is often hindered by the intensive manual effort needed to create labelled training data. This study introduces a synthetic data framework to generate large volumes of richly labelled training data…

Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and…