forked from lcjnil/github-notion-star
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpaper_count.py
87 lines (79 loc) · 13.6 KB
/
paper_count.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
data = """
Wangyou Zhang, Xuankai Chang, Christoph Boeddeker, Tomohiro Nakatani, Shinji Watanabe and Yanmin Qian. End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party. IEEE/ACM Transactions on Audio, Speech, and Language Processing. vol. 30, pp. 3173-3188, 2022. wyz97-zhang-taslp2022.pdf
Yanmin Qian, Xun Gong and Minkun Huang. Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing. vol. 30, pp. 2842-2853, 2022. xg000-taslp2022
Yanmin Qian and Zhikai Zhou. Optimizing Data Usage for Low-Resource Speech Recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing. vol. 30, pp. 394-403, 2022. zzk-taslp2022.pdf
Chenda Li, Zhuo Chen and Yanmin Qian. Dual-Path Modeling With Memory Embedding Model for Continuous Speech Separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing. vol. 30, pp. 1508-1520, 2022. cdl54-taslp2022.pdf
Bo Chen, Chenpeng Du and Kai Yu. Neural Fusion for Voice Cloning. IEEE/ACM Transactions on Audio, Speech, and Language Processing. vol. 30, pp. 1993-2001, 2022. bc299-taslp2022.pdf
Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Xiangzhan Yu and Furu Wei. WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing. IEEE Journal of Selected Topics in Signal Processing. vol. 16, pp. 1505-1518, 2022. zyc97-jstsp22.pdf
徐志航, 陈博, 张辉, 俞凯. 小数据下的音素级别说话人嵌入的语音合成自适应方法. 计算机学报. Vol.45, No.2, pp. 1003-1017, May 2022. zhx66-xu-计算机学报2022.pdf
刘奇, 马饶, 俞凯. 马尔可夫决策过程和先验控制向量在弱约束自然语言生成中的应用. 计算机学报. Vol.45, No.2, pp. 289-301,2022. lq-计算机学报2022.pdf
Zhi Chen, Yuncong Liu, Lu Chen, Su Zhu, Mengyue Wu and Kai Yu. OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue. Transactions of the Association for Computational Linguistics.
Jisen Chen, Jian Shen, Ting Long, Liping Shen, Weinan Zhan, Yong Yu. Heterogeneous Graph Representation for Knowledge Tracing. The 29th International Conference on Neural Information Processing, 2022.
Wei Wang, Wangyou Zhang, Shaoxiong Lin, Yanmin Qian. Text-Informed Knowledge Distillation for Robust Speech Enhancement and Recognition. ISCSLP 2022. ww089-wang-iscslp2022.pdf
Tao Liu, Xu Xiang, Zhengyang Chen, Bing Han, Kai Yu, Yanmin Qian. The X-Lance Speaker Diarization System for the Conversational Short-phrase Speaker Diarization Challenge 2022. ISCSLP 2022. tl123-liu-iscslp2022.pdf
Wenbin Jiang, Tao Liu, Kai Yu. Efficient Speech Enhancement with Neural Homomorphic Synthesis. Proc. Interspeech 2022. 10411. jiang22b_interspeech2022.pdf
Tao Liu, Shuai Fan, Xu Xiang, Hongbo Song, Shaoxiong Lin, Jiaqi Sun, Tianyuan Han, Siyuan Chen, Binwei Yao, Sen Liu, Yifei Wu, Yanmin Qian, Kai Yu. MSDWild: Multi-modal Speaker Diarization Dataset in the Wild. Proc. Interspeech 2022. 10466.tl123-liu-interspeech22.pdf
Chenpeng Du, Yiwei Guo, Xie Chen and Kai Yu. VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature. Proc. Interspeech 2022. 1596-1600.cpd30-du-interspeech22.pdf
Leying Zhang, Zhengyang Chen and Yanmin Qian. Enroll-Aware Attentive Statistics Pooling for Target Speaker Verification. Proc. Interspeech 2022. 311-315.lyz15-zhang-interspeech22.pdf
Bing Han, Zhengyang Chen and Yanmin Qian. Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction. Proc. Interspeech 2022. 4780-4784. bh321-han-interspeech22.pdf
Wangyou Zhang, Zhuo Chen, Naoyuki Kanda, Shujie Liu, Jinyu Li, Sefik Emre Eskimez, Takuya Yoshioka, Xiong Xiao, Zhong Meng, Yanmin Qian and Furu Wei. Separating Long-form Speech with Group-wise Permutation Invariant Training. Proc. Interspeech 2022. 5383-5387. wyz97-zhang-interspeech22.pdf
Yen-Ju Lu, Xuankai Chang, Chenda Li, Wangyou Zhang, Samuele Cornell, Zhaoheng Ni, Yoshiki Masuyama, Brian Yan, Robin Scheibler, Zhong-Qiu Wang, Yu Tsao, Yanmin Qian and Shinji Watanabe. ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding. Proc. Interspeech 2022. 5458-5462. way97-lu-interspeech22.pdf
Xun Gong, Zhikai Zhou and Yanmin Qian. Knowledge Transfer and Distillation from Autoregressive to Non-Autoregressive Speech Recognition. Proc. Interspeech 2022. 2618-2622. xg000-is22
Bei Liu, Zhengyang Chen and Yanmin Qian. Attentive Feature Fusion for Robust Speaker Verification. Proc. Interspeech 2022. 286-290. bl253-liu-interspeech22-1.pdf
Bei Liu, Zhengyang Chen and Yanmin Qian. Dual Path Embedding Learning for Speaker Verification with Triplet Attention. Proc. Interspeech 2022. 291-295. bl253-liu-interspeech22-2.pdf
Bei Liu, Zhengyang Chen, Shuai Wang, Haoyu Wang, Bing Han and Yanmin Qian. DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design. Proc. Interspeech 2022. 296-300. bl253-liu-interspeech22-3.pdf
Zihan Zhao, Lu Chen, Ruisheng Cao, Hongshen Xu, Xingyu Chen and Kai Yu. TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). Seattle, United States, 2022, 1808-1821. zhz73-zhao-naacl22.pdf
Yu Xi, Tian Tan, Wangyou Zhang, Baochen Yang and Kai Yu. Text Adaptive Detection for Customizable Keyword Spotting. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 6652-6656. yx024-xi-icassp22.pdf
Chenda Li, Lei Yang, Weiqin Wang, Yanmin Qian. Skim: Skipping Memory Lstm for Low-Latency Real-Time Continuous Speech Separation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 681-685. cdl54-icassp2022.pdf
Guangwei Li, Xuenan Xu, Mengyue Wu and Kai Yu. Category-Adapted Sound Event Enhancement with Weakly Labeled Data. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 851-855.gwl20-li-icassp22-1.pdf
Guangwei Li, Xuenan Xu, Mengyue Wu and Kai Yu. Navigating Audio-Visual Event Detection Across Mismatched Modalities. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 1975-1979.gwl20-li-icassp22-2.pdf
Siyu Lou, Xuenan Xu, Mengyue Wu and Kai Yu. Audio-Text Retrieval in Context. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 4793-4797. syl92-lou-icassp22.pdf
Xuenan Xu, Mengyue Wu and Kai Yu. Diversity-controllable and Accurate Audio Captioning Based on Neural Condition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 971-975. xnx98-xu-icassp22.pdf
Wen Wu, Mengyue Wu and Kai Yu. Climate and Weather: Inspecting Depression Detection via Emotion Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 6262-6266.myw19-wu-icassp22-1.pdf
Zelin Zhou, Zhiling Zhang, Xuenan Xu, Zeyu Xie, Mengyue Wu and Kenny Q. Zhu. Can Audio Captions Be Evaluated with Image Caption Metrics? IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 981-985. myw19-wu-icassp22-2.pdf
Wei Wang, Shuo Ren, Yao Qian, Shujie Liu, Yu Shi, Yanmin Qian and Michael Zeng. Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 7802-7806. ww089-wang-icassp22-1.pdf
Yifei Wu, Chenda Li, Jinfeng Bai, Zhongqin Wu and Yanmin Qian. Time-domain Audio-visual Speech Separation On Low Quality Videos, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 256-260. yfw51-wu-icassp22.pdf
Wei Wang, Xun Gong, Yifei Wu, Zhikai Zhou, Chenda Li, Wangyou Zhang, Bing Han, Yanmin Qian. The Sjtu System For Multimodal Information Based Speech Processing Challenge 2021. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 9261-9265. ww089-wang-icassp22-2.pdf
Zhengyang Chen ,Sanyuan Chen, Yu Wu, Yao Qian, Chengyi Wang, Shujie Liu, Yanmin Qian and Michael Zeng. Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 6147-6151. zyc97-chen-icassp22-1.pdf
Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li and Xiangzhan Yu. Unispeech-Sat: Universal Speech Representation Learning With Speaker Aware Pre-Training. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 6152-6156. zyc97-chen-icassp22-2.pdf
Bing Han, Zhengyang Chen and Yanmin Qian. Local Information Modeling with Self-Attention for Speaker Verification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 6727-6731. bh321-han-icassp22-1.pdf
Bing Han, Zhengyang Chen , Bei Liu and Yanmin Qian. MLP-SVNET: A Multi-Layer Perceptrons Based Network for Speaker Verification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 7522-7526. bh321-han-icassp22-2.pdf
Yiwei Guo, Chenpeng Du and Kai Yu. Unsupervised word-level prosody tagging for controllable speech synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 7597-7601. ywg11-guo-icassp22.pdf
Bei Liu, Haoyu Wang, Zhengyang Chen, Shuai Wang and Yanmin Qian. Self-Knowledge Distillation via Feature Enhancement for Speaker Verification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 7542-7546. bl253-liu-icassp22.pdf
Lingfeng Dai, Lu Chen, Zhikai Zhou and Kai Yu. LatticeBART: Lattice-to-Lattice Pre-Training for Speech Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 6112-6116. lfd98-dai-icassp22.pdf
Wenbin Jiang, Zhijun Liu, Kai Yu and Fei Wen. Speech enhancement with neural homomorphic synthesis, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 376-380. wbj36-jiang-icassp22.pdf
Zhikai Zhou, Wei Wang, Wangyou Zhang and Yanmin Qian. Exploring Effective Data Utilization for Low-Resource Speech Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 8192-8196. zkz01-zhou-icassp22-1.pdf
Zhikai Zhou, Tian Tan and Yanmin Qian. Punctuation Prediction for Streaming On-Device Speech Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore, 2022, 8192-8196. zkz01-zhou-icassp22-2.pdf
Zhi Chen, Lu Chen, Bei Chen, Libo Qin, Yuncong Liu, Su Zhu, Jian-Guang Lou, and Kai Yu. UniDU: Towards A Unified Generative Dialogue Understanding Framework. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. pages 442–455, Edinburgh, UK. Association for Computational Linguistics. zc825-chen-sigdial22-1.pdf
Zhi Chen, Bei Chen, Lu Chen, Kai Yu and Jian-Guang Lou. AdapterShare: Task Correlation Modeling with Adapter Differentiation.In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022).
Liangtai Sun, Xingyu Chen, Lu Chen, Tianle Dai, Zichen Zhu, Kai Yu. META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI.In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022).
Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Zhu. Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022).
Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Zhu. Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22). syc20-chen-ijcai22.pdf
Binwei Yao, Chao Shi, Likai Zou, Lingfeng Dai, Mengyue Wu, Lu Chen, Zhen Wang, Kai Yu. D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022).
"""
import pandas as pd
parsed = {}
for line in data.split("\n"):
print(line)
details = line.split(".")
details = [d.strip() for d in details if d.strip() != ""]
if len(details) == 0:
continue
if details[-1].endswith("pdf"):
details = details[:-2] # xxx.pdf
authors = [d.strip() for d in details[0].split(",")]
z = authors[-1]
if "and" in z:
authors = authors[:-1]
authors.extend([d.strip() for d in z.split("and")])
name = details[1]
conference = details[2:]
if conference[0].startswith("Proc"): # proc interspeech
conference[0] = conference[0] + ". " + conference[1]
del conference[1]
if len(conference) == 1:
conference.append("") # details
parsed[name] = dict(authors=", ".join(authors), name=name, conference=conference[0], conf_detail=" ".join(conference[1:]))
print(parsed[name])
parsed = pd.DataFrame(parsed)
parsed.T.to_excel("~/Downloads/tmp.xlsx", index=False)