TEDLIUM-3
Emerging11papers using it
2023first seen
TEDLIUM3 is a dataset used for evaluating automatic speech recognition (ASR) models, containing transcribed audio recordings to assess word error rates (WER) in speech recognition tasks.
Papers using TEDLIUM-3 (11)
- Investigating End-to-end ASR Architectures For Long Form Audio TranscriptionFast Word Error Rate Estimation Using Self-supervised Representations For Speech And TextDeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech RecognitionFast Word Error Rate Estimation Using Self-Supervised Representations
for Speech and TextEfficient Long-form Speech Recognition For General Speech In-context LearningEnhancing Quantised End-to-End ASR Models via PersonalisationInvestigating End-to-End ASR Architectures for Long Form Audio
TranscriptionUpdated Corpora and Benchmarks for Long-Form Speech RecognitionSAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASRSpeaker Adaptation for Quantised End-to-End ASR ModelsEfficient Long-Form Speech Recognition for General Speech In-Context
Learning