automatic speech recognition

AutoML for Speech and Language Processing

Universal Speech Model and Language Foundational Models

Speech Translation: Model, Data, Evaluation

Large-Scale and Parameter-Efficient Language Modeling for Speech Processing

CACHING NETWORKS: CAPITALIZING ON COMMON SPEECH FOR ASR

KNOWLEDGE DISTILLATION FROM LANGUAGE MODEL TO ACOUSTIC MODEL: A HIERARCHICAL MULTI-TASK LEARNING APPROACH

SPEECH PATTERN BASED BLACK-BOX MODEL WATERMARKING FOR AUTOMATIC SPEECH RECOGNITION

KNOWLEDGE TRANSFER FROM LARGE-SCALE PRETRAINED LANGUAGE MODELS TO END-TO-END SPEECH RECOGNIZERS

NOISE-ROBUST SPEECH RECOGNITION WITH 10 MINUTES UNPARALLELED IN-DOMAIN DATA

INTEGER-ONLY ZERO-SHOT QUANTIZATION FOR EFFICIENT SPEECH RECOGNITION

TED TALK TEASER GENERATION WITH PRE-TRAINED MODELS

Phone-to-audio alignment without text: A Semi-supervised Approach