Alert button
Picture for Yukun Ma

Yukun Ma

Alert button

ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers

Jan 04, 2024
Chen Zheng, Ke Sun, Da Tang, Yukun Ma, Yuyu Zhang, Chenguang Xi, Xun Zhou

Viaarxiv icon

MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation

Dec 19, 2023
Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Jiaqi Yip, Dianwen Ng, Bin Ma

Viaarxiv icon

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR

Nov 08, 2023
Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Shiliang Zhang, Chong Deng, Yukun Ma, Hai Yu, Jiaqing Liu, Chong Zhang

Figure 1 for Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR
Figure 2 for Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR
Figure 3 for Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR
Figure 4 for Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR
Viaarxiv icon

Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy

Oct 07, 2023
Zheng Zhang, Chen Zheng, Da Tang, Ke Sun, Yukun Ma, Yingtong Bu, Xun Zhou, Liang Zhao

Viaarxiv icon

SPGM: Prioritizing Local Features for enhanced speech separation performance

Sep 22, 2023
Jia Qi Yip, Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Dianwen Ng, Eng Siong Chng, Bin Ma

Figure 1 for SPGM: Prioritizing Local Features for enhanced speech separation performance
Figure 2 for SPGM: Prioritizing Local Features for enhanced speech separation performance
Figure 3 for SPGM: Prioritizing Local Features for enhanced speech separation performance
Figure 4 for SPGM: Prioritizing Local Features for enhanced speech separation performance
Viaarxiv icon

Are Soft Prompts Good Zero-shot Learners for Speech Recognition?

Sep 18, 2023
Dianwen Ng, Chong Zhang, Ruixi Zhang, Yukun Ma, Fabian Ritter-Gutierrez, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng, Bin Ma

Figure 1 for Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
Figure 2 for Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
Figure 3 for Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
Figure 4 for Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
Viaarxiv icon

ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention

May 20, 2023
Jia Qi Yip, Tuan Truong, Dianwen Ng, Chong Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng, Bin Ma

Figure 1 for ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Figure 2 for ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Figure 3 for ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Figure 4 for ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Viaarxiv icon

Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings

May 18, 2023
Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang

Figure 1 for Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Figure 2 for Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Figure 3 for Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Figure 4 for Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Viaarxiv icon

Contrastive Speech Mixup for Low-resource Keyword Spotting

May 02, 2023
Dianwen Ng, Ruixi Zhang, Jia Qi Yip, Chong Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Eng Siong Chng, Bin Ma

Figure 1 for Contrastive Speech Mixup for Low-resource Keyword Spotting
Figure 2 for Contrastive Speech Mixup for Low-resource Keyword Spotting
Figure 3 for Contrastive Speech Mixup for Low-resource Keyword Spotting
Figure 4 for Contrastive Speech Mixup for Low-resource Keyword Spotting
Viaarxiv icon

Adaptive Knowledge Distillation between Text and Speech Pre-trained Models

Mar 07, 2023
Jinjie Ni, Yukun Ma, Wen Wang, Qian Chen, Dianwen Ng, Han Lei, Trung Hieu Nguyen, Chong Zhang, Bin Ma, Erik Cambria

Figure 1 for Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Figure 2 for Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Figure 3 for Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Figure 4 for Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Viaarxiv icon