SLP-P8.1

Contextual Biasing of Named-Entities with Large Language Models

Chuanneng Sun, Rutgers University-New Brunswick, United States of America; Zeeshan Ahmed, Yingyi Ma, Zhe Liu, Lucas Kabela, Yutong Pang, Ozlem Kalinli, Meta, United States of America

Session:
SLP-P8: Resource Constrained Acoustic and Langugage Modeling I Poster

Track:
Speech and Language Processing

Location:
Poster Zone 1B
Poster Board PZ-1B.1

Presentation Time:
Wed, 17 Apr, 13:10 - 15:10 (UTC +9)

Session Co-Chairs:
Hung-yi Lee, National Taiwan University and Hui Wan, Google
View Manuscript
Presentation
Discussion
Resources
Session SLP-P8
SLP-P8.1: Contextual Biasing of Named-Entities with Large Language Models
Chuanneng Sun, Rutgers University-New Brunswick, United States of America; Zeeshan Ahmed, Yingyi Ma, Zhe Liu, Lucas Kabela, Yutong Pang, Ozlem Kalinli, Meta, United States of America
SLP-P8.2: Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble
Zhe Liu, Ozlem Kalinli, Meta, United States of America
SLP-P8.3: SPEAKER-ADAPTIVE LIPREADING VIA SPATIO-TEMPORAL INFORMATION LEARNING
Yi He, Lei Yang, Hanyi Wang, Yun Zhu, Shilin Wang, Shanghai Jiao Tong University, China
SLP-P8.4: A MULTIMODAL APPROACH TO DEVICE-DIRECTED SPEECH DETECTION WITH LARGE LANGUAGE MODELS
Dominik Wagner, Technische Hochschule Nuernberg Georg Simon Ohm, Germany; Alexander Churchill, Siddharth Sigtia, Panayiotis Georgiou, Matt Mirsamadi, Aarshee Mishra, Erik Marchi, Apple, United Kingdom of Great Britain and Northern Ireland
SLP-P8.5: Towards a World-English Language Model for On-Device Virtual Assistants
Rricha Jalota, AppTek GmbH, Germany; Lyan Verwimp, Markus Nussbaum-Thom, Amr Mousa, Arturo Argueta, Youssef Oualil, Apple, Germany
SLP-P8.6: CORRECTION FOCUSED LANGUAGE MODEL TRAINING FOR SPEECH RECOGNITION
Yingyi Ma, Zhe Liu, Ozlem Kalinli, Meta, United States of America
SLP-P8.7: ACOUSTIC BPE FOR SPEECH GENERATION WITH DISCRETE TOKENS
Feiyu Shen, Yiwei Guo, Chenpeng Du, Xie Chen, Kai Yu, Shanghai Jiao Tong University, China
SLP-P8.8: STUDY OF ABUSE DETECTION IN CONTINUOUS SPEECH FOR INDIAN LANGUAGES
Rini Sharon, IIT Madras, India; Debdoot Mukherjee, Meesho, India
SLP-P8.9: TURN-TAKING AND BACKCHANNEL PREDICTION WITH ACOUSTIC AND LARGE LANGUAGE MODEL FUSION
Jinhan Wang, University of California, Los Angeles, United States of America; Long Chen, Aparna Khare, Anirudh Raju, Pranav Dheram, Di He, Minhua Wu, Amazon, United States of America; Andreas Stolcke, Uniphore, United States of America; Venkatesh Ravichandran, Amazon, United States of America
Contacts