Powerful and Extensible WFST Framework for RNN-Transducer Losses

Powerful and Extensible WFST Framework for RNN-Transducer Losses

18 March 2023

Vladimir Bataev

Boris Ginsburg

Papers citing "Powerful and Extensible WFST Framework for RNN-Transducer Losses"

6 / 6 papers shown

Title
RNN-Transducer-based Losses for Speech Recognition on Noisy Targets Vladimir Bataev 35 0 0 09 Apr 2025
TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer Vladimir Bataev Subhankar Ghosh Vitaly Lavrukhin Jason Chun Lok Li AI4TS 41 0 0 10 Jan 2025
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework Eliya Segev Maya Alroy Ronen Katsir Noam Wies Ayana Shenhav ... D. Zar Oren Tadmor Jacob Bitterman Amnon Shashua Tal Rosenwein 30 2 0 04 Jul 2023
CTC Variations Through New WFST Topologies A. Laptev Somshubra Majumdar Boris Ginsburg 34 20 0 06 Oct 2021
Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition Chao Weng Chengzhu Yu Jia Cui Chunlei Zhang Dong Yu 77 39 0 28 Nov 2019
NeMo: a toolkit for building AI applications using Neural Modules Oleksii Kuchaiev Jason Chun Lok Li Huyen Nguyen Oleksii Hrinchuk Ryan Leary ... Jack Cook P. Castonguay Mariya Popova Jocelyn Huang Jonathan M. Cohen 211 292 0 14 Sep 2019