相关论文: Leveraging Language Model Capabilities for Sound E…

State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal…

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…

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…

Respiratory diseases remain major global health challenges, and traditional auscultation is often limited by subjectivity, environmental noise, and inter-clinician variability. This study presents an explainable multimodal deep learning…

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

Segmental models are sequence prediction models in which scores of hypotheses are based on entire variable-length segments of frames. We consider segmental models for whole-word ("acoustic-to-word") speech recognition, with the feature…

This paper addresses the noisy label issue in audio event detection (AED) by refining strong labels as sequential labels with inaccurate timestamps removed. In AED, strong labels contain the occurrence of a specific event and its timestamps…

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…

We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time…

Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…

Detection of common events and scenes from audio is useful for extracting and understanding human contexts in daily life. Prior studies have shown that leveraging knowledge from a relevant domain is beneficial for a target acoustic event…

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

In this paper, we introduce our recent studies on human perception in audio event classification by different deep learning models. In particular, the pre-trained model VGGish is used as feature extractor to process audio data, and DenseNet…

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The classification performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds.…

In this paper, we study the use of soft labels to train a system for sound event detection (SED). Soft labels can result from annotations which account for human uncertainty about categories, or emerge as a natural representation of…

Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…

The increasing success of audio foundation models across various tasks has led to a growing need for improved interpretability to understand their intricate decision-making processes better. Existing methods primarily focus on explaining…