Word spotting, VAD, and other topics in speech recognition

Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization

Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation

Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Models

Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting

ON WORD ERROR RATE DEFINITIONS AND THEIR EFFICIENT COMPUTATION FOR MULTI-SPEAKER SPEECH RECOGNITION SYSTEMS

Towards trustworthy phoneme boundary detection with autoregressive model and improved evaluation metric

SLOT-TRIGGERED CONTEXTUAL BIASING FOR PERSONALIZED SPEECH RECOGNITION USING NEURAL TRANSDUCERS

Multitask Detection of Speaker Changes, Overlapping Speech and Voice Activity Using wav2vec 2.0

Towards Accurate and Real-time End-of-speech Estimation

Gaussian process dynamical modeling for adaptive inference over graphs

SMALL-FOOTPRINT SLIMMABLE NETWORKS FOR KEYWORD SPOTTING

METRIC LEARNING FOR USER-DEFINED KEYWORD SPOTTING