相关论文: UniCon: Unified Context Network for Robust Active …

Speech applications are expected to be low-power and robust under noisy conditions. An effective Voice Activity Detection (VAD) front-end lowers the computational need. Spiking Neural Networks (SNNs) are known to be biologically plausible…

The development of neural audio codecs (NACs) has largely promoted applications of language models (LMs) to speech processing and understanding. However, there lacks the verification on the effectiveness of autoregressive (AR) LMbased…

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these…

Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data, with wide applications such as industrial inspection and medical analysis, where anomalies are scarce due to privacy…

This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including…

Speaker recognition is a biometric modality that utilizes the speaker's speech segments to recognize the identity, determining whether the test speaker belongs to one of the enrolled speakers. In order to improve the robustness of the…

In next-generation wireless networks, supporting real-time applications such as augmented reality, autonomous driving, and immersive Metaverse services demands stringent constraints on bandwidth, latency, and reliability. Existing semantic…

Anomalous sound detection (ASD) is one of the most significant tasks of mechanical equipment monitoring and maintaining in complex industrial systems. In practice, it is vital to precisely identify abnormal status of the working mechanical…

Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low…

Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own…

Whispering is a ubiquitous mode of communication that humans use daily. Despite this, whispered speech has been poorly served by existing speech technology due to a shortage of resources and processing methodology. To remedy this, this…

Interview performance assessment is essential for determining candidates' suitability for professional positions. To ensure holistic and fair evaluations, we propose a novel and comprehensive framework that explores ``365'' aspects of…

The pooling layer is an essential component in the neural network based speaker verification. Most of the current networks in speaker verification use average pooling to derive the utterance-level speaker representations. Average pooling…

Recognizing the sounding objects in scenes is a longstanding objective in embodied AI, with diverse applications in robotics and AR/VR/MR. To that end, Audio-Visual Segmentation (AVS), taking as condition an audio signal to identify the…

In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a…

Keyword spotting (KWS) and speaker verification (SV) have been studied independently although it is known that acoustic and speaker domains are complementary. In this paper, we propose a multi-task network that performs KWS and SV…

Audio-visual speaker recognition is one of the tasks in the recent 2019 NIST speaker recognition evaluation (SRE). Studies in neuroscience and computer science all point to the fact that vision and auditory neural signals interact in the…