From 949d32e33a7212884a063619576c5c211551246f Mon Sep 17 00:00:00 2001 From: Dongji Gao Date: Thu, 28 Sep 2023 15:06:15 -0400 Subject: [PATCH] Update README.md 1. Add OTC paper link 2. Add OTC bibtex 3. Add pre-trained model link --- egs/librispeech/WSASR/README.md | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/egs/librispeech/WSASR/README.md b/egs/librispeech/WSASR/README.md index 0a06c7984..3b8822fd2 100644 --- a/egs/librispeech/WSASR/README.md +++ b/egs/librispeech/WSASR/README.md @@ -1,7 +1,7 @@ # Introduction This is a weakly supervised ASR recipe for the LibriSpeech (clean 100 hours) dataset. We train a -conformer model using [Bypass Temporal Classification](https://arxiv.org/pdf/2306.01031.pdf) (BTC)/Omni-temporal Classification (OTC) with transcripts with synthetic errors. In this README, we will describe +conformer model using [Bypass Temporal Classification](https://arxiv.org/pdf/2306.01031.pdf) (BTC)/[Omni-temporal Classification](https://arxiv.org/pdf/2309.15796.pdf) (OTC) with transcripts with synthetic errors. In this README, we will describe the task and the BTC/OTC training process. Note that OTC is an extension of BTC and supports all BTC functions. Therefore, in the following, we only describe OTC. @@ -203,6 +203,9 @@ export CUDA_VISIBLE_DEVICES="0" +## Pre-trained Model +Pre-trained model: + ## Citations ``` @inproceedings{gao2023bypass, @@ -211,4 +214,11 @@ export CUDA_VISIBLE_DEVICES="0" booktitle={INTERSPEECH}, year={2023} } + +@inproceedings{gao2023learning, + title={Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition}, + author={Gao, Dongji and Xu, Hainan and Raj, Desh and Garcia, Leibny Paola and Povey, Daniel and Khudanpur, Sanjeev}, + booktitle={IEEE ASRU}, + year={2023} +} ```