Resource constrained speech recognition

Papez: Resource-efficient Speech Separation with Auditory Working Memory

Improving Accented Speech Recognition with Multi-Domain Training

DOMAIN AND LANGUAGE ADAPTATION USING HETEROGENEOUS DATASETS FOR WAV2VEC2.0-BASED SPEECH RECOGNITION OF LOW-RESOURCE LANGUAGE

Ensemble knowledge distillation of self-supervised speech models

WeavSpeech: Data Augmentation Strategy for Automatic Speech Recognition via Semantic-Aware Weaving

MoLE : MIXTURE OF LANGUAGE EXPERTS FOR MULTI-LINGUAL AUTOMATIC SPEECH RECOGNITION

Dynamic Chunk Convolution for Unified Streaming and Non-Streaming Conformer ASR

Gated contextual adapters for selective contextual biasing in neural transducers

SG-VAD: STOCHASTIC GATES BASED SPEECH ACTIVITY DETECTION

EURO: ESPnet Unsupervised ASR Open-source Toolkit

Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning

MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition