ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2211.00896
  4. Cited By
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural
  Transducers

Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers

2 November 2022
Duc Le
Frank Seide
Yuhao Wang
Heng Chang
Kjell Schubert
Ozlem Kalinli
M. Seltzer
ArXivPDFHTML

Papers citing "Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers"

7 / 7 papers shown
Title
Boosting Hybrid Autoregressive Transducer-based ASR with Internal
  Acoustic Model Training and Dual Blank Thresholding
Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
Takafumi Moriya
Takanori Ashihara
Masato Mimura
Hiroshi Sato
Kohei Matsuura
Ryo Masumura
Taichi Asami
29
0
0
30 Sep 2024
CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based
  Speech Recognition
CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
Junfeng Hou
Peiyao Wang
Jincheng Zhang
Meng Yang
Minwei Feng
Jingcheng Yin
31
1
0
04 Jan 2024
Improved Factorized Neural Transducer Model For text-only Domain
  Adaptation
Improved Factorized Neural Transducer Model For text-only Domain Adaptation
Jing Liu
Jianwei Yu
Xie Chen
48
1
0
18 Sep 2023
Folding Attention: Memory and Power Optimization for On-Device
  Transformer-based Streaming Speech Recognition
Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Yang Li
Liangzhen Lai
Shangguan Yuan
Forrest N. Iandola
Zhaoheng Ni
Ernie Chang
Yangyang Shi
Vikas Chandra
34
2
0
14 Sep 2023
A Token-Wise Beam Search Algorithm for RNN-T
A Token-Wise Beam Search Algorithm for RNN-T
Gil Keren
36
2
0
28 Feb 2023
Less Is More: Improved RNN-T Decoding Using Limited Label Context and
  Path Merging
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging
Rohit Prabhavalkar
Yanzhang He
David Rybach
S. Campbell
A. Narayanan
Trevor Strohman
Tara N. Sainath
58
35
0
12 Dec 2020
Emformer: Efficient Memory Transformer Based Acoustic Model For Low
  Latency Streaming Speech Recognition
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
Yangyang Shi
Yongqiang Wang
Chunyang Wu
Ching-Feng Yeh
Julian Chan
Frank Zhang
Duc Le
M. Seltzer
58
168
0
21 Oct 2020
1