diff --git a/speechx/README.md b/speechx/README.md
index 610b88a8fe6a3acb62e74258095677827d729267..34a662786f4b1c5acb1213d0cb7ec798ec22ad26 100644
--- a/speechx/README.md
+++ b/speechx/README.md
@@ -3,7 +3,7 @@
 ## Environment
 
 We develop under:
-* docker - registry.baidubce.com/paddlepaddle/paddle:2.1.1-gpu-cuda10.2-cudnn7
+* docker - `registry.baidubce.com/paddlepaddle/paddle:2.2.2-gpu-cuda10.2-cudnn7`
 * os - Ubuntu 16.04.7 LTS
 * gcc/g++/gfortran - 8.2.0
 * cmake - 3.16.0
@@ -19,7 +19,7 @@ We develop under:
 1. First to launch docker container.
 
 ```
-nvidia-docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/workspace --name=dev registry.baidubce.com/paddlepaddle/paddle:2.1.1-gpu-cuda10.2-cudnn7 /bin/bash
+docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/workspace --name=dev registry.baidubce.com/paddlepaddle/paddle:2.2.2-gpu-cuda10.2-cudnn7 /bin/bash
 ```
 
 * More `Paddle` docker images you can see [here](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/docker/linux-docker.html).
@@ -60,4 +60,5 @@ popd
 
 ## TODO
 
+### Deepspeech2 with linear feature
 * DecibelNormalizer: there is a little bit difference between offline and online db norm. The computation of online db norm read feature chunk by chunk, which causes the feature size is different with offline db norm. In normalizer.cc:73, the samples.size() is different, which causes the difference of result.
diff --git a/speechx/build.sh b/speechx/build.sh
index 8e36d23367346e2a68168c2954f224c845f75e15..a6eef65655be50f661ccd1f0aaaf5b1decbc0f1e 100755
--- a/speechx/build.sh
+++ b/speechx/build.sh
@@ -22,6 +22,6 @@ cd build
 cmake .. -DBOOST_ROOT:STRING=${boost_SOURCE_DIR}
 #cmake .. 
 
-make -j10
+make -j
 
 cd -
diff --git a/speechx/examples/ds2_ol/websocket/websocket_client_main.cc b/speechx/examples/ds2_ol/websocket/websocket_client_main.cc
index 68ea898adc06b0a97e257369e4d5312fc6bf37de..d6f0d4806ce9ff17a1cb9564b499576e12adbd0b 100644
--- a/speechx/examples/ds2_ol/websocket/websocket_client_main.cc
+++ b/speechx/examples/ds2_ol/websocket/websocket_client_main.cc
@@ -18,7 +18,7 @@
 #include "kaldi/util/table-types.h"
 
 DEFINE_string(host, "127.0.0.1", "host of websocket server");
-DEFINE_int32(port, 201314, "port of websocket server");
+DEFINE_int32(port, 8082, "port of websocket server");
 DEFINE_string(wav_rspecifier, "", "test wav scp path");
 DEFINE_double(streaming_chunk, 0.1, "streaming feature chunk size");
 
diff --git a/speechx/examples/ds2_ol/websocket/websocket_server_main.cc b/speechx/examples/ds2_ol/websocket/websocket_server_main.cc
index 43cbd6bbc28175bc36c0f85f215f52e370f26df7..109da96b68db0fd0ae13df2da2841c4bbf40882d 100644
--- a/speechx/examples/ds2_ol/websocket/websocket_server_main.cc
+++ b/speechx/examples/ds2_ol/websocket/websocket_server_main.cc
@@ -15,7 +15,7 @@
 #include "websocket/websocket_server.h"
 #include "decoder/param.h"
 
-DEFINE_int32(port, 201314, "websocket listening port");
+DEFINE_int32(port, 8082, "websocket listening port");
 
 int main(int argc, char *argv[]) {
     gflags::ParseCommandLineFlags(&argc, &argv, false);