-
DDNet: A task-decoupled two-stage network for multi-channel speech denoising and dereverberatio
Author: Yan, Hengyu; Yang, Ruidi; Wei, Zijie; Mao, Yuxing
Journal: SPEECH COMMUNICATION. 2026; Vol. 180, Issue , pp. -. DOI: 10.1016/j.specom.2026.103394
-
MaTSE: A hybrid Mamba-Transformer model for monaural Speech Enhancemen
Author: Zhou, Hao; Zhou, Yi; Zhao, Yu; Liu, Yin
Journal: SPEECH COMMUNICATION. 2026; Vol. 180, Issue , pp. -. DOI: 10.1016/j.specom.2026.103395
-
AVFSNet: Audio-visual speech separation for flexible number of speakers with multi-scale and multi-task learnin
Author: Zhang, Daning; Deng, Yuanjie; Wei, Ying; Ji, Bing
Journal: SPEECH COMMUNICATION. 2026; Vol. 179, Issue , pp. -. DOI: 10.1016/j.specom.2026.103378
-
Viseme identification ability and its effect on auditory consonant perception in Mandarin-speaking younger and older adult
Author: Xu, Min; Shao, Jing; Ding, Hongwei
Journal: SPEECH COMMUNICATION. 2026; Vol. 179, Issue , pp. -. DOI: 10.1016/j.specom.2026.103376
-
Exploring one-formant vowel perception in real speech corpus through typicality assessmen
Author: Yu, Shuiyuan; Xu, Chunshan; Liu, Haitao
Journal: SPEECH COMMUNICATION. 2026; Vol. 179, Issue , pp. -. DOI: 10.1016/j.specom.2026.103375
-
Cross-attention fusion for audio-visual emotion recognition with shared transforme
Author: Lei, Jianjun; Ye, Kai; Wang, Ying
Journal: SPEECH COMMUNICATION. 2026; Vol. 178, Issue , pp. -. DOI: 10.1016/j.specom.2026.103356
-
Emphasis rendering for conversational text-to-speech with multi-modal multi-scale context modelin
Author: Liu, Rui; Jia, Zhenqi; Yang, Jie; Hu, Yifan; Li, Haizhou
Journal: SPEECH COMMUNICATION. 2026; Vol. 178, Issue , pp. -. DOI: 10.1016/j.specom.2026.103353
-
MS-VBRVQ: Multi-scale variable bitrate speech residual vector quantizatio
Author: Qian, Yukun; Xu, Shiyun; Zhuang, Xuyi; Zhang, Zehua; Wang, Mingjiang
Journal: SPEECH COMMUNICATION. 2026; Vol. 177, Issue , pp. -. DOI: 10.1016/j.specom.2025.103346
