尽管
发表于 2025-3-25 03:26:55
http://reply.papertrans.cn/63/6221/622081/622081_21.png
insurgent
发表于 2025-3-25 08:49:22
http://reply.papertrans.cn/63/6221/622081/622081_22.png
periodontitis
发表于 2025-3-25 15:34:45
http://reply.papertrans.cn/63/6221/622081/622081_23.png
surmount
发表于 2025-3-25 19:43:21
http://reply.papertrans.cn/63/6221/622081/622081_24.png
小步舞
发表于 2025-3-25 22:49:20
http://reply.papertrans.cn/63/6221/622081/622081_25.png
daredevil
发表于 2025-3-26 03:57:00
http://reply.papertrans.cn/63/6221/622081/622081_26.png
初学者
发表于 2025-3-26 04:20:25
,Semantic Enhancement Framework for Robust Speech Recognition,t of the ASR system will provide input to the subsequent system, the semantic intelligibility problem of the recognition results draws wide attention, yet remains unsolved. We propose a semantic enhancement framework to extract global semantic information from the audio to guide the recognition resu
滔滔不绝的人
发表于 2025-3-26 09:41:22
http://reply.papertrans.cn/63/6221/622081/622081_28.png
厌烦
发表于 2025-3-26 12:51:00
Predictive AutoEncoders Are Context-Aware Unsupervised Anomalous Sound Detectors,he conventional unsupervised ASD approaches mainly employ the straightforward deep neural network (DNN) to detect abnormal sounds. However, this model fails to consider the utilization of the relationship between frames, resulting in limited performance and constrained input length. Recently, contex
indecipherable
发表于 2025-3-26 18:25:30
,A Pipelined Framework with Serialized Output Training for Overlapping Speech Recognition,paper, we focus on solving the problem of overlapping speech and present a pipelined architecture with serialized output training(SOT). The baseline and the proposed methods are evaluated on the artificially mixed speech datasets generated from the AliMeeting corpus. Experimental results demonstrate