Related papers: A Reference-free Metric for Language-Queried Audio…

Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which…

Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity,…

Automatic lyrics transcription (ALT) remains a challenging task in the field of music information retrieval, despite great advances in automatic speech recognition (ASR) brought about by transformer-based architectures in recent years. One…

We propose the Fr\'echet Audio Distance (FAD), a novel, reference-free evaluation metric for music enhancement algorithms. We demonstrate how typical evaluation metrics for speech enhancement and blind source separation can fail to…

Contrastive learning constitutes an emerging branch of self-supervised learning that leverages large amounts of unlabeled data, by learning a latent space, where pairs of different views of the same sample are associated. In this paper, we…

Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing. Its employment ranges from sound event detection to text-to-audio generation. However, one of the main limitations is…

Over the past few decades, computational methods have been developed to estimate perceptual audio quality. These methods, also referred to as objective quality measures, are usually developed and intended for a specific application domain.…

Although text-to-audio generation has made remarkable progress in realism and diversity, the development of evaluation metrics has not kept pace. Widely-adopted approaches, typically based on embedding similarity like CLAPScore, effectively…

Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics…

We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a…

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

Source separation is a fundamental task in speech, music, and audio processing, and it also provides cleaner and larger data for training generative models. However, improving separation performance in practice often depends on increasingly…

Automatic speech recognition systems often produce confident yet incorrect transcriptions under noisy or ambiguous conditions, which can be misleading for both users and downstream applications. Standard evaluation based on Word Error Rate…

Audio source separation aims to separate a mixture into target sources. Previous audio source separation systems usually conduct one-step inference, which does not fully explore the separation ability of models. In this work, we reveal that…

Source separation is the task to separate an audio recording into individual sound sources. Source separation is fundamental for computational auditory scene analysis. Previous work on source separation has focused on separating particular…

To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are…

Cinematic Audio Source Separation (CASS) aims to decompose mixed film audio into speech, music, and sound effects, enabling applications like dubbing and remastering. Existing CASS approaches are audio-only, overlooking the inherent…

Referenceless metrics (e.g., CLIPScore) use pretrained vision--language models to assess image descriptions directly without costly ground-truth reference texts. Such methods can facilitate rapid progress, but only if they truly align with…

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

The objective speech quality assessment is usually conducted by comparing received speech signal with its clean reference, while human beings are capable of evaluating the speech quality without any reference, such as in the mean opinion…