Librispeech 960h
Emerging13papers using it
2021first seen
Papers using Librispeech 960h (13)
- A Comparative Analysis on ASR System Combination for Attention, CTC, Factored Hybrid, and Transducer ModelsIML-Spikeformer: Input-aware Multi-Level Spiking Transformer for Speech ProcessingRight Label Context in End-to-End Training of Time-Synchronous ASR
ModelsContrastive Siamese Network for Semi-supervised Speech RecognitionHierarchical Conditional End-to-End ASR with CTC and Multi-Granular
Subword UnitsMake More of Your Data: Minimal Effort Data Augmentation for Automatic
Speech Recognition and TranslationDomain Adaptation of low-resource Target-Domain models using
well-trained ASR Conformer ModelsDynamic Latency for CTC-Based Streaming Automatic Speech Recognition
With EmformerBayesSpeech: A Bayesian Transformer Network for Automatic Speech
RecognitionCompetitive and Resource Efficient Factored Hybrid HMM Systems are
Simpler Than You ThinkFast-HuBERT: An Efficient Training Framework for Self-Supervised Speech
Representation LearningContextualized Automatic Speech Recognition with Attention-Based Bias
Phrase Boosted Beam SearchInvestigating the Effect of Label Topology and Training Criterion on ASR
Performance and Alignment Quality