17 citations · 43 across the 13 of their papers we have counts for
14 papers
Hidden-Domain Routing for All-Type Audio Deepfake Detection
Yifan Gao, Yao Tian, Hongbin Suo +1
All-type audio deepfake detection requires authenticity decisions across speech, environmental sound, singing voice, and music, while the audio type is unavailable at inference tim…
Robust LLM-based Audio-Visual Speech Recognition with Sparse Modality Alignment and Visual Unit-Guided Refinement
Fei Su, Cancan Li, Juan Liu +3
Audio-Visual Speech Recognition (AVSR) integrates acoustic and visual information to enhance robustness in adverse acoustic conditions. Recent advances in Large Language Models (LL…
Vclip: Face-based Speaker Generation by Face-voice Association Learning
Yao Shi, Yunfei Xu, Hongbin Suo +2
This paper discusses the task of face-based speech synthesis, a kind of personalized speech synthesis where the synthesized voices are constrained to perceptually match with a refe…
Multi-channel multi-speaker transformer for speech recognition
Guo Yifan, Tian Yao, Suo Hongbin +1
With the development of teleconferencing and in-vehicle voice assistants, far-field multi-speaker speech recognition has become a hot research topic. Recently, a multi-channel tran…
AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines
Cancan Li, Fei Su, Juan Liu +4
Whisper speech recognition is crucial not only for ensuring privacy in sensitive communications but also for providing a critical communication bridge for patients under vocal rest…
The Database and Benchmark for the Source Speaker Tracing Challenge 2024
Ze Li, Yuke Lin, Tian Yao +6
Voice conversion (VC) systems can transform audio to mimic another speaker's voice, thereby attacking speaker verification (SV) systems. However, ongoing studies on source speaker…
Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning
Yucong Zhang, Hongbin Suo, Yulong Wan +1
This paper proposes an approach for anomalous sound detection that incorporates outlier exposure and inlier modeling within a unified framework by multitask learning. While outlier…
Task-Agnostic Structured Pruning of Speech Representation Models
Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang +2
Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks. However, their large memory and strong computatio…
Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models
Haoyu Wang, Wei-Qiang Zhang, Hongbin Suo +1
Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perfo…
PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification
Siqi Zheng, Hongbin Suo, Qian Chen
Speaker embedding has been a fundamental feature for speaker-related tasks such as verification, clustering, and diarization. Traditionally, speaker embeddings are represented as f…
Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure
Siqi Zheng, Hongbin Suo
Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods hav…
Graph Convolutional Network Based Semi-Supervised Learning on Multi-Speaker Meeting Data
Fuchuan Tong, Siqi Zheng, Min Zhang +4
Unsupervised clustering on speakers is becoming increasingly important for its potential uses in semi-supervised learning. In reality, we are often presented with enormous amounts…
BeamTransformer: Microphone Array-based Overlapping Speech Detection
Siqi Zheng, Shiliang Zhang, Weilong Huang +5
We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling. BeamTransformer…
A Real-time Speaker Diarization System Based on Spatial Spectrum
Siqi Zheng, Weilong Huang, Xianliang Wang +3
In this paper we describe a speaker diarization system that enables localization and identification of all speakers present in a conversation or meeting. We propose a novel systema…