Showing 1–14 of 14 results
/ Date/ Name
Jul 1, 2019Improving Performance of End-to-End ASR on Numeric SequencesAug 24, 2020Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text CorpusAug 28, 2022Towards Disentangled Speech RepresentationsJan 11, 2023Dual Learning for Large Vocabulary On-Device ASRMay 19, 2020Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss CriterionAug 11, 2023Improving Joint Speech-Text Representations Without AlignmentApr 19, 2023A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at ScaleMar 28, 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and LatencyNov 28, 2022E2E Segmentation in a Two-Pass Cascaded Encoder ASR ModelApr 22, 2022E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASRMar 9, 2022Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech RecognitionApr 9, 2021Lookup-Table Recurrent Language Models for Long Tail Speech RecognitionApr 15, 2022Improving Rare Word Recognition with LM-aware MWER TrainingJun 5, 2024Text Injection for Neural Contextual Biasing