87 citations · 224 across the 60 of their papers we have counts for
10 papers · 1 filter
MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation
Yanjie Fu, Haoran Yin, Meng Ge +5
Recently, many deep learning based beamformers have been proposed for multi-channel speech separation. Nevertheless, most of them rely on extra cues known in advance, such as speak…
Monolingual Recognizers Fusion for Code-switching Speech Recognition
Tongtong Song, Qiang Xu, Haoyu Lu +5
The bi-encoder structure has been intensively investigated in code-switching (CS) automatic speech recognition (ASR). However, most existing methods require the structures of two m…
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
Xiaohui Liu, Meng Liu, Lin Zhang +7
The Audio Deep Synthesis Detection (ADD) Challenge has been held to detect generated human-like speech. With our submitted system, this paper provides an overall assessment of trac…
VCSE: Time-Domain Visual-Contextual Speaker Extraction Network
Junjie Li, Meng Ge, Zexu Pan +2
Speaker extraction seeks to extract the target speech in a multi-talker scenario given an auxiliary reference. Such reference can be auditory, i.e., a pre-recorded speech, visual,…
Language-specific Characteristic Assistance for Code-switching Speech Recognition
Tongtong Song, Qiang Xu, Meng Ge +5
Dual-encoder structure successfully utilizes two language-specific encoders (LSEs) for code-switching speech recognition. Because LSEs are initialized by two pre-trained language-s…
MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources
Haoran Yin, Meng Ge, Yanjie Fu +5
Recent neural network based Direction of Arrival (DoA) estimation algorithms have performed well on unknown number of sound sources scenarios. These algorithms are usually achieved…
Iterative Sound Source Localization for Unknown Number of Sources
Yanjie Fu, Meng Ge, Haoran Yin +4
Sound source localization aims to seek the direction of arrival (DOA) of all sound sources from the observed multi-channel audio. For the practical problem of unknown number of sou…
Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning
Cuiying Huo, Dongxiao He, Yawen Li +5
Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. Most existing HGNN-based approaches are supervised or s…
TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding
Ruiteng Zhang, Jianguo Wei, Xugang Lu +6
Speaker embedding is an important front-end module to explore discriminative speaker features for many speech applications where speaker information is needed. Current SOTA backbon…
L-SpEx: Localized Target Speaker Extraction
Meng Ge, Chenglin Xu, Longbiao Wang +3
Speaker extraction aims to extract the target speaker's voice from a multi-talker speech mixture given an auxiliary reference utterance. Recent studies show that speaker extraction…