Accented Speech Recognition
4 papers with code • 4 benchmarks • 26 datasets
Benchmarks
These leaderboards are used to track progress in Accented Speech Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Accented Speech Recognition models and implementationsDatasets
-
VoxForge
-
1,025 Hours - Mandarin Strong Accent Speech Data by Mobile Phone
-
794 Hours - Sichuan Dialect Speech Data by Mobile Phone
-
997 Hours – Wuhan Dialect Speech Data by Mobile Phone
-
520 Hours - French Speaking English Speech Data by Mobile Phone
-
388 Hours - Spanish Speaking English Speech Data by Mobile Phone
-
201 Hours - Singaporean Speaking English Speech Data by Mobile Phone
-
227 Hours - Italian Speaking English Speech Data by Mobile Phone
-
800 Hours - Sichuan Dialect Conversational Speech Data by Mobile Phone
-
Cantonese Conversational Speech Data
Most implemented papers
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages.
Deep Speech: Scaling up end-to-end speech recognition
We present a state-of-the-art speech recognition system developed using end-to-end deep learning.
Coupled Training of Sequence-to-Sequence Models for Accented Speech Recognition
vinitunni/CoupledLoss-LAS-ESPNet
•
•
We propose coupled training for encoder-decoder ASR models that acts on pairs of utterances corresponding to the same text spoken by speakers with different accents.
Goodness of Pronunciation Pipelines for OOV Problem
In the following report we propose pipelines for Goodness of Pronunciation (GoP) computation solving OOV problem at testing time using Vocab/Lexicon expansion techniques.
