Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation-Reference-Cited by-同舟云学术

Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation

Published:2021-12-13 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
language:
Short-container-title:

Author:

Zhang Qinglin¹,Chen Qian¹,Li Yali¹,Liu Jiaqing²,Wang Wen¹

Affiliation:

1. Alibaba Group,Speech Lab

2. Renmin University of China

Publisher

IEEE

Link

Reference20 articles.

2. Two-level transformer and auxiliary coherence modeling for im-proved text segmentation;glavas;AAAI,0

3. Google's neural machine translation system: Bridging the gap between human and machine translation;yonghui;CoRR,2016

4. BERT: pre-training of deep bidi-rectional transformers for language understanding;devlin;NAACL-HLT,2019

5. Roberta: A ro-bustly optimized BERT pretraining approach;liu;CoRR,2019

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

2. MUG: A General Meeting Understanding and Generation Benchmark;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

3. The Ajmide Topic Segmentation System for the ICASSP 2023 General Meeting Understanding and Generation Challenge;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04