Search Results for author:
Found 8 papers, 3 papers with code
DEM: Distribution Edited Model for Training with Mixed Data Distributions
Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models.
HLAT: High-quality Large Language Model Pre-trained on AWS Trainium
In this paper, we showcase HLAT: a family of 7B and 70B decoder-only LLMs pre-trained using 4096 AWS Trainium accelerators over 1. 8 trillion tokens.
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer
These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence.
Neural Network based End-to-End Query by Example Spoken Term Detection
Here, we show that the CNN based matching outperforms DTW based matching using bottleneck features as well.
Multilingual Bottleneck Features for Query by Example Spoken Term Detection
State of the art solutions to query by example spoken term detection (QbE-STD) usually rely on bottleneck feature representation of the query and audio document to perform dynamic time warping (DTW) based template matching.
Document-Level Neural Machine Translation with Hierarchical Attention Networks
Neural Machine Translation (NMT) can be improved by including document-level contextual information.
Self-Attentive Residual Decoder for Neural Machine Translation
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation.
A Bayesian Approach to Estimation of Speaker Normalization Parameters
In this work, a Bayesian approach to speaker normalization is proposed to compensate for the degradation in performance of a speaker independent speech recognition system.
