Titlebook: Man-Machine Speech Communication; 18th National Confer Jia Jia,Zhenhua Ling,Zixing Zhang Conference proceedings 2024 The Editor(s) (if appl

GROWL

,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

,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

Console

6Applepolish

,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

,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

,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

electrolyte

Palliation

,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