Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Yulan Liu

Yulan Liu

Multi-turn RNN-T for streaming recognition of multi-party speech

Dec 19, 2021
Ilya Sklyar, Anna Piunova, Xianrui Zheng, Yulan Liu

Figure 1 for Multi-turn RNN-T for streaming recognition of multi-party speech

Figure 2 for Multi-turn RNN-T for streaming recognition of multi-party speech

Figure 3 for Multi-turn RNN-T for streaming recognition of multi-party speech

Figure 4 for Multi-turn RNN-T for streaming recognition of multi-party speech

* Submitted to ICASSP2022

Access Paper or Ask Questions

SynthASR: Unlocking Synthetic Data for Speech Recognition

Jun 14, 2021
Amin Fazel, Wei Yang, Yulan Liu, Roberto Barra-Chicote, Yixiong Meng, Roland Maas, Jasha Droppo

Figure 1 for SynthASR: Unlocking Synthetic Data for Speech Recognition

Figure 2 for SynthASR: Unlocking Synthetic Data for Speech Recognition

Figure 3 for SynthASR: Unlocking Synthetic Data for Speech Recognition

Figure 4 for SynthASR: Unlocking Synthetic Data for Speech Recognition

* Accepted to Interspeech 2021

Access Paper or Ask Questions

Streaming Multi-speaker ASR with RNN-T

Nov 23, 2020
Ilya Sklyar, Anna Piunova, Yulan Liu

Figure 1 for Streaming Multi-speaker ASR with RNN-T

Figure 2 for Streaming Multi-speaker ASR with RNN-T

Figure 3 for Streaming Multi-speaker ASR with RNN-T

Access Paper or Ask Questions

Equivalent Lipschitz surrogates for zero-norm and rank optimization problems

Apr 30, 2018
Yulan Liu, Shujun Bi, Shaohua Pan

Figure 1 for Equivalent Lipschitz surrogates for zero-norm and rank optimization problems

Figure 2 for Equivalent Lipschitz surrogates for zero-norm and rank optimization problems

Access Paper or Ask Questions

The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media

Dec 21, 2015
Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond W. M. Ng, Madina Hasan, Yulan Liu, Thomas Hain

Figure 1 for The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media

Figure 2 for The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media

Figure 3 for The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media

Figure 4 for The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media

* IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), 13-17 Dec 2015, Scottsdale, Arizona, USA

Access Paper or Ask Questions