SLP-P34: Resource Constrained Acoustic and Langugage Modeling II
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)
Location: Poster Zone 1B
Session Type: Poster
Session Co-Chairs: Hung-yi Lee, National Taiwan University and Zoltan Tuske, AppTek
Track: Speech and Language Processing
Click the to view the manuscript on IEEE Xplore Open Preview
 

SLP-P34.1: ACCENT-SPECIFIC VECTOR QUANTIZATION FOR JOINT UNSUPERVISED AND SUPERVISED TRAINING IN ACCENT ROBUST SPEECH RECOGNITION
Li Li, Shanghai Normal University, China; Yijie Li, Dongxing Xu, Unisound AI Technology Co., Ltd., China; Haoran Wei, University of Texas at Dallas, Richardson, TX 75080, United States of America; Yanhua Long, Shanghai Normal University, China
 

SLP-P34.2: TODM: TRAIN ONCE DEPLOY MANY EFFICIENT SUPERNET-BASED RNN-T COMPRESSION FOR ON-DEVICE ASR MODELS
Yuan Shangguan, Haichuan Yang, Meta, United States of America; Danni Li, N/A, United States of America; Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra, Meta, United States of America
 

SLP-P34.3: A CROSS SEARCH METHOD FOR DATA AUGMENTATION IN NEURAL MACHINE TRANSLATION
Mengchao Zhang, Mei Tu, Fan Zhang, Song Liu, Samsung Research China - Beijing (SRC-B), China
 

SLP-P34.4: RESIDUALTRANSFORMER: RESIDUAL LOW-RANK LEARNING WITH WEIGHT-SHARING FOR TRANSFORMER LAYERS
Yiming Wang, Jinyu Li, Microsoft Corporation, United States of America
 

SLP-P34.5: ROBUST SPEAKER PERSONALISATION USING GENERALIZED LOW-RANK ADAPTATION FOR AUTOMATIC SPEECH RECOGNITION
Arun Baby, George Joseph, Shatrughan Singh, Samsung, India
 

SLP-P34.6: DISTILLING HUBERT WITH LSTMS VIA DECOUPLED KNOWLEDGE DISTILLATION
Danilo de Oliveira, Timo Gerkmann, Universität Hamburg, Germany
 

SLP-P34.7: IMPROVING SPEED/ACCURACY TRADEOFF FOR ONLINE STREAMING ASR VIA REAL-VALUED AND TRAINABLE STRIDES
Dario Albesano, Nicola Ferri, Felix Weninger, Puming Zhan, Microsoft, Italy
 

SLP-P34.8: Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Yang Li, Liangzhen Lai, Yuan Shangguan, Forrest N. Iandola, Zhaoheng Ni, Ernie Chang, Yangyang Shi, Vikas Chandra, Meta AI, United States of America
 

SLP-P34.9: Enhancing Quantised End-to-End ASR Models via Personalisation
Qiuming Zhao, Tsinghua University, China; Guangzhi Sun, University of Cambridge, China; Chao Zhang, Mingxing Xu, Thomas Fang Zheng, Tsinghua University, China