On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “RNN-T”

Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Losscs.CL

This study improves knowledge distillation for RNN-T models with noisy labels.

problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.

method Full-sum distillation and sequence-level knowledge distillation.

result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.

knowledge distillation RNN-T models noisy labels sequence-level distillation full-sum distillation

2023-03-10abs ↗pdf ↗

A New Training Pipeline for an Improved Neural Transducereess.AS

Improved neural transducer model outperforms attention model on longer sequences.

problem Improving performance of neural transducer models.

method Comparison of training criteria (marginalization vs. maximum approximation), model generalization, and output label topology.

result Final transducer model outperforms attention model by over 6% relative WER on Switchboard 300h.

neural transducer end-to-end model RNN-T RNA CTC

2020-05-19abs ↗pdf ↗

Improving Performance of End-to-End ASR on Numeric Sequenceseess.AS

Recognizing written domain numeric utterances (e.g. I need $1.25.) can be challenging for ASR systems, particularly when numeric sequences are not seen during training. This out-of-vocabulary (OOV) issue is addressed in conventional ASR systems by training part of the model on spoken domain utterances (e.g. I need one …

2019-07-01abs ↗pdf ↗