New algorithms and approaches for speech recognition

Joint Discriminator and Transfer Based Fast Domain Adaptation for End-to-End Speech Recognition

A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One

Once-for-All Sequence Compression for Self-Supervised Speech Models

SPEECH AND NOISE DUAL-STREAM SPECTROGRAM REFINE NETWORK WITH SPEECH DISTORTION LOSS FOR ROBUST SPEECH RECOGNITION

USING MODIFIED ADULT SPEECH AS DATA AUGMENTATION FOR CHILD SPEECH RECOGNITION

M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval

FIXED-POINT QUANTIZATION AWARE TRAINING FOR ON-DEVICE KEYWORD-SPOTTING

SPEECH-TEXT BASED MULTI-MODAL TRAINING WITH BIDIRECTIONAL ATTENTION FOR IMPROVED SPEECH RECOGNITION

Learning Cross-lingual Visual Speech Representations

IMPROVING FAIRNESS AND ROBUSTNESS IN END-TO-END SPEECH RECOGNITION THROUGH UNSUPERVISED CLUSTERING

Cleanformer: A Multichannel Array Configuration-Invariant Neural Enhancement Frontend for ASR in Smart Speakers

IMPORTANCE OF DIFFERENT TEMPORAL MODULATIONS OF SPEECH: A TALE OF TWO PERSPECTIVES