Cheng-I Lai

1.6k total citations · 2 hit papers
14 papers, 875 citations indexed

About

Cheng-I Lai is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Cheng-I Lai has authored 14 papers receiving a total of 875 indexed citations (citations by other indexed papers that have themselves been cited), including 14 papers in Artificial Intelligence, 6 papers in Signal Processing and 3 papers in Computer Vision and Pattern Recognition. Recurrent topics in Cheng-I Lai's work include Speech Recognition and Synthesis (10 papers), Natural Language Processing Techniques (9 papers) and Topic Modeling (6 papers). Cheng-I Lai is often cited by papers focused on Speech Recognition and Synthesis (10 papers), Natural Language Processing Techniques (9 papers) and Topic Modeling (6 papers). Cheng-I Lai collaborates with scholars based in United States, Taiwan and Japan. Cheng-I Lai's co-authors include James Glass, Nanxin Chen, Yuan Gong, Yu-An Chung, Hung-yi Lee, Yung-Sung Chuang, Jesús Villalba, Najim Dehak, Shang-Wen Li and Shinji Watanabe and has published in prestigious journals such as Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Proceedings of the AAAI Conference on Artificial Intelligence and ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

In The Last Decade

Cheng-I Lai

13 papers receiving 830 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

SUPERB: Speech Processing Universal PERformance Benchmark

2021 409 citations Shu-Wen Yang, Po-Han Chi et al. profile →
SSAST: Self-Supervised Audio Spectrogram Transformer

2022 146 citations Yuan Gong, Cheng-I Lai et al. Proceedings of the AAAI Conference on Artificial Intelligence profile →

Peers

Cheng-I Lai

AI

SP

CVPR

ECP

PHYSI

Brecht Desplanques Belgium

Jenthe Thienpondt Belgium

Xuankai Chang United States

Jiatong Shi United States

Longbiao Wang China

Shinnosuke Takamichi Japan

Sachin Kajarekar United States

Tsubasa Ochiai Japan

Kushal Lakhotia Israel

František Grézl Czechia

Brecht Desplanques Belgium

Cheng-I Lai

819 ×1.1

AI

737 ×1.3

SP

85 ×0.8

CVPR

50 ×0.6

ECP

32 ×1.1

PHYSI

Citations per year, relative to Cheng-I Lai Cheng-I Lai (= 1×) peers Brecht Desplanques

Countries citing papers authored by Cheng-I Lai

Since Specialization

Citations

This map shows the geographic impact of Cheng-I Lai's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Cheng-I Lai with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Cheng-I Lai more than expected).

Fields of papers citing papers by Cheng-I Lai

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Cheng-I Lai. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Cheng-I Lai. The network helps show where Cheng-I Lai may publish in the future.

Co-authorship network of co-authors of Cheng-I Lai

This figure shows the co-authorship network connecting the top 25 collaborators of Cheng-I Lai. A scholar is included among the top collaborators of Cheng-I Lai based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Cheng-I Lai. Cheng-I Lai is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

14 of 14 papers shown

1.

Lai, Cheng-I, et al.. (2023). Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences. 1–5. 1 indexed citations

2.

Lai, Cheng-I, Freda Shi, Yoon Kim, et al.. (2023). Audio-Visual Neural Syntax Acquisition. 1–8.

3.

Liu, Alexander, et al.. (2022). Cross-Modal Discrete Representation Learning. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 3013–3035. 24 indexed citations

4.

Lai, Cheng-I, Erica Cooper, Yang Zhang, et al.. (2022). On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8447–8451. 3 indexed citations

5.

Lai, Cheng-I, et al.. (2022). Simple and Effective Unsupervised Speech Synthesis. Interspeech 2022. 843–847. 9 indexed citations

6.

Gong, Yuan, Cheng-I Lai, Yu-An Chung, & James Glass. (2022). SSAST: Self-Supervised Audio Spectrogram Transformer. Proceedings of the AAAI Conference on Artificial Intelligence. 36(10). 10699–10709. 146 indexed citations breakdown →

7.

Yang, Shu-Wen, Po-Han Chi, Yung-Sung Chuang, et al.. (2021). SUPERB: Speech Processing Universal PERformance Benchmark. 1194–1198. 409 indexed citations breakdown →

8.

Lai, Cheng-I, Yung-Sung Chuang, Hung-yi Lee, Shang-Wen Li, & James Glass. (2021). Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining. 7468–7472. 35 indexed citations

9.

Cooper, Erica, Cheng-I Lai, Yusuke Yasuda, et al.. (2020). Zero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings. 6184–6188. 98 indexed citations

10.

Lai, Cheng-I, et al.. (2020). Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction. 8 indexed citations

11.

Cooper, Erica, Cheng-I Lai, Yusuke Yasuda, & Junichi Yamagishi. (2020). Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?. 3979–3983. 14 indexed citations

12.

Lai, Cheng-I, Nanxin Chen, Jesús Villalba, & Najim Dehak. (2019). ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks. 1013–1017. 102 indexed citations

13.

Guo, Jialiang, et al.. (2019). Controlling the Reading Level of Machine Translation Output. 193–203. 15 indexed citations

14.

Nidadavolu, Phani Sankar, Cheng-I Lai, Jesús Villalba, & Najim Dehak. (2018). Investigation on Bandwidth Extension for Speaker Recognition. 1111–1115. 11 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact