diff --git a/_typos.toml b/_typos.toml
index f33e24cba51..92ea00cff15 100644
--- a/_typos.toml
+++ b/_typos.toml
@@ -39,7 +39,6 @@ Similarily = "Similarily"
 Simle = "Simle"
 Sovler = "Sovler"
 Successed = "Successed"
-accoustic = "accoustic"
 classfy = "classfy"
 contxt = "contxt"
 convertion = "convertion"
diff --git a/docs/design/network/deep_speech_2.md b/docs/design/network/deep_speech_2.md
index aaaab971bb5..31520fbd778 100644
--- a/docs/design/network/deep_speech_2.md
+++ b/docs/design/network/deep_speech_2.md
@@ -102,7 +102,7 @@ Issue for each task will be created later. Contributions, discussions and commen
 
 ### Overview
 
-Traditional **ASR** (Automatic Speech Recognition) pipelines require great human efforts devoted to elaborately tuning multiple hand-engineered components (e.g. audio feature design, accoustic model, pronuncation model and language model etc.). **Deep Speech 2** (**DS2**) \[[1](#references)\], however, trains such ASR models in an end-to-end manner, replacing most intermediate modules with only a single deep network architecture. With scaling up both the data and model sizes, DS2 achieves a very significant performance boost.
+Traditional **ASR** (Automatic Speech Recognition) pipelines require great human efforts devoted to elaborately tuning multiple hand-engineered components (e.g. audio feature design, acoustic model, pronuncation model and language model etc.). **Deep Speech 2** (**DS2**) \[[1](#references)\], however, trains such ASR models in an end-to-end manner, replacing most intermediate modules with only a single deep network architecture. With scaling up both the data and model sizes, DS2 achieves a very significant performance boost.
 
 Please read Deep Speech 2 \[[1](#references),[2](#references)\] paper for more background knowledge.