Xinkang Xu

机构：Voith (United States) · ORCID：0009-0003-2771-1398

发表论文 34 篇 · 总被引 122 次 · h-index 7

代表论文

• LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement (2023 · 被引 16)
• Multiple Enhancements to LSTM for Learning Emotion-Salient Features in Speech Emotion Recognition (2022 · Interspeech 2022 · 被引 11)
• Semi-supervised Multimodal Emotion Recognition with Consensus Decision-making and Label Correction (2023 · 被引 9)
• SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR (2024 · 被引 7)
• A Deep Representation Learning-Based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder (2024 · 被引 7)
• Learning Emotion-Invariant Speaker Representations for Speaker Verification (2024 · 被引 5)