RETURNN: The RWTH Extensible Training framework for Universal Recurrent
Neural Networks

RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks

2 August 2016

P. Voigtlaender

Papers citing "RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks"

11 / 11 papers shown

Title
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder Khai Le-Duc Phuc Phan Tan-Hanh Pham Bach Phan Tat Minh-Huong Ngo Chris Ngo Thanh Nguyen-Tang Truong-Son Hy LM&MA 48 0 0 21 Sep 2024
Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality Tina Raissi Christoph Luscher Simon Berger Ralf Schluter Hermann Ney 34 2 0 16 Jul 2024
Efficient Utilization of Large Pre-Trained Models for Low Resource ASR Peter Vieting Christoph Luscher Julian Dierkes Ralf Schluter Hermann Ney 38 5 0 26 Oct 2022
AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task P. Wilken E. Matusov 24 4 0 12 May 2022
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures Nick Rossenbach Mohammad Zeineldeen Benedikt Hilmes Ralf Schluter Hermann Ney 28 12 0 12 Apr 2021
Early Stage LM Integration Using Local and Global Log-Linear Combination Wilfried Michel Ralf Schluter Hermann Ney 11 11 0 20 May 2020
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems Nick Rossenbach Albert Zeyer Ralf Schluter Hermann Ney 18 83 0 19 Dec 2019
Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech T. Menne Ilya Sklyar Ralf Schluter Hermann Ney 22 35 0 09 May 2019
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation Christoph Luscher Eugen Beck Kazuki Irie M. Kitza Wilfried Michel Albert Zeyer Ralf Schluter Hermann Ney VLM 13 234 0 08 May 2019
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition Albert Zeyer Tamer Alkhouli Hermann Ney 37 90 0 14 May 2018
A comprehensive study of batch construction strategies for recurrent neural networks in MXNet P. Doetsch Pavel Golik Hermann Ney 32 17 0 05 May 2017