From e6d49d086f481465f6e0ce6dc68cc8afbab266e2 Mon Sep 17 00:00:00 2001
From: smohan-speech <smohan@mail.ustc.edu.cn>
Date: Thu, 11 May 2023 10:07:32 +0800
Subject: [PATCH] add speaker-attributed ASR task for alimeeting

---
 egs/alimeeting/sa-asr/README.md    | 18 +++++++++---------
 egs/alimeeting/sa-asr/asr_local.sh | 21 +++++++++++++++------
 2 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/egs/alimeeting/sa-asr/README.md b/egs/alimeeting/sa-asr/README.md
index 882345c25..5731c39eb 100644
--- a/egs/alimeeting/sa-asr/README.md
+++ b/egs/alimeeting/sa-asr/README.md
@@ -1,7 +1,7 @@
 # Get Started
 Speaker Attributed Automatic Speech Recognition (SA-ASR) is a task proposed to solve "who spoke what". Specifically, the goal of SA-ASR is not only to obtain multi-speaker transcriptions, but also to identify the corresponding speaker for each utterance. The method used in this example is referenced in the paper: [End-to-End Speaker-Attributed ASR with Transformer](https://www.isca-speech.org/archive/pdfs/interspeech_2021/kanda21b_interspeech.pdf).  
 To run this receipe, first you need to install FunASR and ModelScope. ([installation](https://alibaba-damo-academy.github.io/FunASR/en/installation.html))  
-There are two startup scripts, `run.sh` for training and evaluating on the old eval and test sets, and `run_m2met_2023_infer.sh` for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 ([M2MET2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)) Challenge.  
+There are two startup scripts, `run.sh` for training and evaluating on the old eval and test sets, and `run_m2met_2023_infer.sh` for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 ([M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)) Challenge.  
 Before running `run.sh`, you must manually download and unpack the [AliMeeting](http://www.openslr.org/119/) corpus and place it in the `./dataset` directory:
 ```shell
 dataset
@@ -61,17 +61,17 @@ The results of the baseline system are as follows. The baseline results include
 	</tr>
     <tr>
 	    <td>oracle profile</td>
-        <td>31.93</td>
-        <td>32.75</td>
-	    <td>48.56</td>
-        <td>53.33</td>
+        <td>32.05</td>
+        <td>32.70</td>
+	    <td>47.40</td>
+        <td>52.57</td>
 	</tr>
     <tr>
 	    <td>cluster profile</td>
-        <td>31.94</td>
-        <td>32.77</td>
-	    <td>55.49</td>
-        <td>58.17</td>
+        <td>32.05</td>
+        <td>32.70</td>
+	    <td>53.76</td>
+        <td>55.95</td>
 	</tr>
 </table>
 
diff --git a/egs/alimeeting/sa-asr/asr_local.sh b/egs/alimeeting/sa-asr/asr_local.sh
index f8cdcd3b6..389bb0158 100755
--- a/egs/alimeeting/sa-asr/asr_local.sh
+++ b/egs/alimeeting/sa-asr/asr_local.sh
@@ -1320,8 +1320,11 @@ if ! "${skip_eval}"; then
             _data="${data_feats}/${dset}"
             _dir="${asr_exp}/${inference_tag}/${dset}"
 
-            python utils/proce_text.py ${_data}/text ${_data}/text.proc
-            python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
+            sed 's/\$//g' ${_data}/text > ${_data}/text_nosrc
+            sed 's/\$//g' ${_dir}/text > ${_dir}/text_nosrc
+
+            python utils/proce_text.py ${_data}/text_nosrc ${_data}/text.proc
+            python utils/proce_text.py ${_dir}/text_nosrc ${_dir}/text.proc
 
             python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
             tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
@@ -1430,8 +1433,11 @@ if ! "${skip_eval}"; then
             _data="${data_feats}/${dset}"
             _dir="${sa_asr_exp}/${sa_asr_inference_tag}.oracle/${dset}"
 
-            python utils/proce_text.py ${_data}/text ${_data}/text.proc
-            python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
+            sed 's/\$//g' ${_data}/text > ${_data}/text_nosrc
+            sed 's/\$//g' ${_dir}/text > ${_dir}/text_nosrc
+
+            python utils/proce_text.py ${_data}/text_nosrc ${_data}/text.proc
+            python utils/proce_text.py ${_dir}/text_nosrc ${_dir}/text.proc
 
             python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
             tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
@@ -1546,8 +1552,11 @@ if ! "${skip_eval}"; then
             _data="${data_feats}/${dset}"
             _dir="${sa_asr_exp}/${sa_asr_inference_tag}.cluster/${dset}"
 
-            python utils/proce_text.py ${_data}/text ${_data}/text.proc
-            python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
+            sed 's/\$//g' ${_data}/text > ${_data}/text_nosrc
+            sed 's/\$//g' ${_dir}/text > ${_dir}/text_nosrc
+
+            python utils/proce_text.py ${_data}/text_nosrc ${_data}/text.proc
+            python utils/proce_text.py ${_dir}/text_nosrc ${_dir}/text.proc
 
             python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
             tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt