相关论文: Large-Scale Learning on Overlapped Speech Detectio…

Accurate alignment of dysfluent speech with intended text is crucial for automating the diagnosis of neurodegenerative speech disorders. Traditional methods often fail to model phoneme similarities effectively, limiting their performance.…

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…

Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single model. However, current state-of-the-art ASR models are typically evaluated on…

A common problem for automatic speech recognition systems is how to recognize words that they did not see during training. Currently there is no established method of evaluating different techniques for tackling this problem. We propose…

Fake speech detection systems have become a necessity to combat against speech deepfakes. Current systems exhibit poor generalizability on out-of-domain speech samples due to lack to diverse training data. In this paper, we attempt to…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

Full-duplex spoken dialogue systems promise to transform human-machine interaction from a rigid, turn-based protocol into a fluid, natural conversation. However, the central challenge to realizing this vision, managing overlapping speech,…

Automatic Speech Recognition (ASR) has been extensively investigated, yet prior benchmarks have largely focused on assessing the acoustic robustness of ASR models, leaving evaluations of their linguistic capabilities relatively…

Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area…

Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while…

There is a gap in the understanding of occluded objects in existing large-scale visual language multi-modal models. Current state-of-the-art multi-modal models fail to provide satisfactory results in describing occluded objects through…

The rise of Omni-modal Large Language Models (OLLMs), which integrate visual and auditory processing with text, necessitates robust safety evaluations to mitigate harmful outputs. However, no dedicated benchmarks currently exist for OLLMs,…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain tasks through fine-tuning, specialized LLMs remain…

Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from the known test set (positive), a scenario referred to as…

In this work, we propose an overlapped speech detection system trained as a three-class classifier. Unlike conventional systems that perform binary classification as to whether or not a frame contains overlapped speech, the proposed…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive…

Time series anomaly detection (TSAD) plays a crucial role in various industries by identifying atypical patterns that deviate from standard trends, thereby maintaining system integrity and enabling prompt response measures. Traditional TSAD…

Sentence Representation Learning (SRL) is a fundamental task in Natural Language Processing (NLP), with the Contrastive Learning of Sentence Embeddings (CSE) being the mainstream technique due to its superior performance. An intriguing…