Cheng-I Lai

发表

Improving Self-Supervised Speech Representations by Disentangling Speakers

M. Hasegawa-Johnson, Shiyu Chang, Yang Zhang, 2022, ArXiv.

Controlling the Reading Level of Machine Translation Output

Philipp Koehn, Cheng-I Lai, Kelly Marchisio, 2019, MTSummit.

Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining pdf

Shang-Wen Li, James R. Glass, James Glass, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SUPERB: Speech processing Universal PERformance Benchmark

Andy T. Liu, Yist Y. Lin, Abdel-rahman Mohamed, 2021, Interspeech.

ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers

M. Hasegawa-Johnson, Shiyu Chang, Yang Zhang, 2022, ICML.

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing

Yingyan Lin, Kaizhi Qian, Cheng-I Lai, 2022, NeurIPS.

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

James R. Glass, Alexander H. Liu, Shiyu Chang, 2021, NeurIPS.

Zero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings

J. Yamagishi, Xin Eric Wang, Nanxin Chen, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SSAST: Self-Supervised Audio Spectrogram Transformer

James R. Glass, Yuan Gong, Cheng-I Lai, 2021, AAAI.

SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities

Andy T. Liu, Abdel-rahman Mohamed, Hung-yi Lee, 2022, ACL.

Simple and Effective Unsupervised Speech Synthesis

James R. Glass, Alexander H. Liu, Michael Auli, 2022, INTERSPEECH.

Cross-Modal Discrete Representation Learning pdf

James Glass, James R. Glass, Aude Oliva, 2021, ACL.

Attentive Filtering Networks for Audio Replay Attack Detection

Simon King, Junichi Yamagishi, Najim Dehak, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?

Junichi Yamagishi, Yusuke Yasuda, Erica Cooper, 2020, INTERSPEECH.

Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences

Hung-yi Lee, Cheng-I Lai, Yuan Tseng, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks

Nanxin Chen, Najim Dehak, Jesús Villalba, 2019, INTERSPEECH.

Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration pdf

Fan-Keng Sun, Cheng-I Lai, Cheng-I Lai, 2020, ArXiv.

Contrastive Predictive Coding Based Feature for Automatic Speaker Verification pdf

Cheng-I Lai, Cheng-I Lai, 2019, ArXiv.

Towards Semi-Supervised Semantics Understanding from Speech pdf

Shang-Wen Li, Jin Cao, Cheng-I Lai, 2020, ArXiv.