Showing 1–19 of 19 results
/ Date/ Name
Oct 28, 2025FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLMsJan 19, 2024Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speechAug 31, 2023Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech SignalsAug 16, 2023Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) TransductionNov 19, 2021Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languagesDec 14, 2020A review of on-device fully neural end-to-end automatic speech recognition algorithmsJan 2, 2020Attention based on-device streaming speech recognition with large speech corpusAug 17, 2023Refining a Deep Learning-based Formant Tracker using Linear Prediction MethodsOct 1, 2022Multi-stage Progressive Compression of Conformer Transducer for On-device Speech RecognitionDec 28, 2019Improved Multi-Stage Training of Online Attention-based Encoder-Decoder ModelsOct 28, 2025zFLoRA: Zero-Latency Fused Low-Rank AdaptersJan 5, 2022Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural NetworksNov 19, 2021A comparison of streaming models and data augmentation methods for robust speech recognitionDec 22, 2019power-law nonlinearity with maximally uniform distribution criterion for improved neural network training in automatic speech recognitionDec 22, 2019end-to-end training of a large vocabulary end-to-end speech recognition systemDec 15, 2023On the compression of shallow non-causal ASR models using knowledge distillation and tied-and-reduced decoder for low-latency on-device speech recognitionJan 8, 2022Two-Pass End-to-End ASR Model CompressionMay 4, 2021Streaming end-to-end speech recognition with jointly trained neural feature enhancementNov 13, 2024Physics Informed Distillation for Diffusion Models