GROWL
发表于 2025-3-26 21:25:09
,Joint Speech and Noise Estimation Using SNR-Adaptive Target Learning for Deep-Learning-Based Speeche estimation network and validate the adaptability of the target learning strategy with the noise prediction branch. We demonstrate the effectiveness of our proposed method on a public benchmark, achieving a significant relative word error rate (WER) reduction of approximately 37% compared to the WER results obtained from unprocessed noisy speech.
Ventricle
发表于 2025-3-27 01:38:40
,Accent-VITS: Accent Transfer for End-to-End TTS,e disentanglement of accent and speaker timbre becomes be more stable and effective. Experiments on multi-accent and Mandarin datasets show that Accent-VITS achieves higher speaker similarity, accent similarity and speech naturalness as compared with a strong baseline (Demos: .).
钻孔
发表于 2025-3-27 08:51:37
http://reply.papertrans.cn/63/6221/622082/622082_33.png
Console
发表于 2025-3-27 10:46:18
http://reply.papertrans.cn/63/6221/622082/622082_34.png
6Applepolish
发表于 2025-3-27 16:03:02
,Semi-End-to-End Nested Named Entity Recognition from Speech,rrors are inevitable. In the E2E approach, its annotation method poses a challenge to Automatic Speech Recognition (ASR) when Named Entities (NEs) are nested. This is because multiple special tokens without audio signals between words will exist, which may even cause ambiguity problems for NER. In t
paragon
发表于 2025-3-27 21:37:33
,A Lightweight Music Source Separation Model with Graph Convolution Network,wever, most of them primarily focus on improving their separation performance, while ignoring the issue of model size in the real-world environments. For the application in the real-world environments, in this paper, we propose a lightweight network combined with the Graph convolutional network Atte
用肘
发表于 2025-3-27 23:00:11
,Joint Time-Domain and Frequency-Domain Progressive Learning for Single-Channel Speech Enhancement alean target, which may introduce speech distortions and limit ASR performance. Meanwhile, these methods usually focus on either the time or frequency domain, ignoring their potential connections. To tackle these problems, we propose a joint time and frequency domain progressive learning (TFDPL) meth
Foregery
发表于 2025-3-28 02:38:32
http://reply.papertrans.cn/63/6221/622082/622082_38.png
electrolyte
发表于 2025-3-28 09:41:27
http://reply.papertrans.cn/63/6221/622082/622082_39.png
Palliation
发表于 2025-3-28 11:22:01
,Within- and Between-Class Sample Interpolation Based Supervised Metric Learning for Speaker Verific methods may suffer from inadequate and low-quality sample pairs, resulting unsatisfactory speaker verification (SV) performance. To address this issue, we propose the data augmentation methods in the embedding space to guarantee sufficient and high-quality negative points for metric learning, terme