activity
20192023
most citedReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

15 citations · 31 across the 9 of their papers we have counts for

collaborators

10 papers

eess.AS2023

CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning

Wei Liu, Zhiyuan Peng, Tan Lee

Transformer-based speech recognition (ASR) model with deep layers exhibited significant performance improvement. However, the model is inefficient for deployment on resource-constr…

eess.AS2023★ 1 cited

Sparsely Shared LoRA on Whisper for Child Speech Recognition

Wei Liu, Ying Qin, Zhiyuan Peng +1

Whisper is a powerful automatic speech recognition (ASR) model. Nevertheless, its zero-shot performance on low-resource speech requires further improvement. Child speech, as a repr…

cs.CL2023★ 15 cited

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

Binfeng Xu, Zhiyuan Peng, Bowen Lei +3

Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution. Existing ALM s…

cs.SD2022

Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition

Zhiyuan Peng, Xuanji He, Ke Ding +2

Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-devi…

cs.SD2022

Covariance Regularization for Probabilistic Linear Discriminant Analysis

Zhiyuan Peng, Mingjie Shao, Xuanji He +4

Probabilistic linear discriminant analysis (PLDA) is commonly used in speaker verification systems to score the similarity of speaker embeddings. Recent studies improved the perfor…

cs.SD2022

Unifying Cosine and PLDA Back-ends for Speaker Verification

Zhiyuan Peng, Xuanji He, Ke Ding +2

State-of-art speaker verification (SV) systems use a back-end model to score the similarity of speaker embeddings extracted from a neural network model. The commonly used back-end…