diff --git a/src/armnnTfLiteParser/TfLiteParser.cpp b/src/armnnTfLiteParser/TfLiteParser.cpp
index 479fc4f..5dbb5ee 100644
--- a/src/armnnTfLiteParser/TfLiteParser.cpp
+++ b/src/armnnTfLiteParser/TfLiteParser.cpp
@@ -1,5 +1,5 @@
 //
-// Copyright © 2017 Arm Ltd and Contributors. All rights reserved.
+// Copyright © 2022 Arm Ltd and Contributors. All rights reserved.
 // SPDX-License-Identifier: MIT
 //
 
@@ -710,6 +710,7 @@
             = &TfLiteParserImpl::ParseLocalResponseNormalization;
     m_ParserFunctions[tflite::BuiltinOperator_LOGICAL_NOT]             = &TfLiteParserImpl::ParseLogicalNot;
     m_ParserFunctions[tflite::BuiltinOperator_LOGISTIC]                = &TfLiteParserImpl::ParseLogistic;
+    m_ParserFunctions[tflite::BuiltinOperator_LOG_SOFTMAX]             = &TfLiteParserImpl::ParseLogSoftmax;
     m_ParserFunctions[tflite::BuiltinOperator_L2_NORMALIZATION]        = &TfLiteParserImpl::ParseL2Normalization;
     m_ParserFunctions[tflite::BuiltinOperator_MAX_POOL_2D]             = &TfLiteParserImpl::ParseMaxPool2D;
     m_ParserFunctions[tflite::BuiltinOperator_MAXIMUM]                 = &TfLiteParserImpl::ParseMaximum;
@@ -1874,6 +1875,33 @@
     RegisterOutputSlots(subgraphIndex, operatorIndex, layer, {outputTensorIndexes[0]});
 }
 
+void TfLiteParserImpl::ParseLogSoftmax(size_t subgraphIndex, size_t operatorIndex)
+{
+    CHECK_MODEL(m_Model, subgraphIndex, operatorIndex);
+
+    LogSoftmaxDescriptor desc;
+
+    auto inputs = GetInputs(m_Model, subgraphIndex, operatorIndex);
+    CHECK_VALID_SIZE(inputs.size(), 1);
+    auto outputs = GetOutputs(m_Model, subgraphIndex, operatorIndex);
+    CHECK_VALID_SIZE(outputs.size(), 1);
+
+    auto layerName = fmt::format("LogSoftmax:{}:{}", subgraphIndex, operatorIndex);
+    IConnectableLayer* const layer = m_Network->AddLogSoftmaxLayer(desc, layerName.c_str());
+
+    armnn::TensorInfo outputTensorInfo = ToTensorInfo(outputs[0], true);
+    layer->GetOutputSlot(0).SetTensorInfo(outputTensorInfo);
+
+    // register the input connection slots for the layer, connections are made after all layers have been created
+    // only the tensors for the inputs are relevant, exclude the const tensors
+    auto inputTensorIndexes = AsUnsignedVector(GetInputTensorIds(m_Model, subgraphIndex, operatorIndex));
+    RegisterInputSlots(subgraphIndex, operatorIndex, layer, {inputTensorIndexes[0]});
+
+    // register the output connection slots for the layer, connections are made after all layers have been created
+    auto outputTensorIndexes = AsUnsignedVector(GetOutputTensorIds(m_Model, subgraphIndex, operatorIndex));
+    RegisterOutputSlots(subgraphIndex, operatorIndex, layer, {outputTensorIndexes[0]});
+}
+
 void TfLiteParserImpl::ParseSpaceToBatchND(size_t subgraphIndex, size_t operatorIndex)
 {
     CHECK_MODEL(m_Model, subgraphIndex, operatorIndex);
diff --git a/src/armnnTfLiteParser/TfLiteParser.hpp b/src/armnnTfLiteParser/TfLiteParser.hpp
index 3fc7205..43c5466 100644
--- a/src/armnnTfLiteParser/TfLiteParser.hpp
+++ b/src/armnnTfLiteParser/TfLiteParser.hpp
@@ -1,5 +1,5 @@
 //
-// Copyright © 2017 Arm Ltd. All rights reserved.
+// Copyright © 2022 Arm Ltd and Contributors. All rights reserved.
 // SPDX-License-Identifier: MIT
 //
 #pragma once
@@ -146,6 +146,7 @@
     void ParseLocalResponseNormalization(size_t subgraphIndex, size_t operatorIndex);
     void ParseLogicalNot(size_t subgraphIndex, size_t operatorIndex);
     void ParseLogistic(size_t subgraphIndex, size_t operatorIndex);
+    void ParseLogSoftmax(size_t subgraphIndex, size_t operatorIndex);
     void ParseL2Normalization(size_t subgraphIndex, size_t operatorIndex);
     void ParseMaxPool2D(size_t subgraphIndex, size_t operatorIndex);
     void ParseMaximum(size_t subgraphIndex, size_t operatorIndex);
diff --git a/src/armnnTfLiteParser/test/LogSoftmax.cpp b/src/armnnTfLiteParser/test/LogSoftmax.cpp
new file mode 100644
index 0000000..7414bc3
--- /dev/null
+++ b/src/armnnTfLiteParser/test/LogSoftmax.cpp
@@ -0,0 +1,70 @@
+//
+// Copyright © 2022 Arm Ltd and Contributors. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#include "ParserFlatbuffersFixture.hpp"
+
+
+TEST_SUITE("TensorflowLiteParser_LogSoftmax")
+{
+struct LogSoftmaxFixture : public ParserFlatbuffersFixture
+{
+    explicit LogSoftmaxFixture()
+    {
+        m_JsonString = R"(
+            {
+                "version": 3,
+                "operator_codes": [ { "builtin_code": "LOG_SOFTMAX" } ],
+                "subgraphs": [ {
+                    "tensors": [
+                        {
+                            "shape": [ 1, 7 ],
+                            "type": "UINT8",
+                            "buffer": 0,
+                            "name": "inputTensor",
+                            "quantization": {
+                                "min": [ 0.0 ],
+                                "max": [ 255.0 ],
+                                "scale": [ 1.0 ],
+                                "zero_point": [ 0 ],
+                            }
+                        },
+                        {
+                            "shape": [ 1, 7 ],
+                            "type": "UINT8",
+                            "buffer": 1,
+                            "name": "outputTensor",
+                            "quantization": {
+                                "min": [ 0.0 ],
+                                "max": [ 255.0 ],
+                                "scale": [ 0.00390625 ],
+                                "zero_point": [ 0 ],
+                            }
+                        }
+                    ],
+                    "inputs": [ 0 ],
+                    "outputs": [ 1 ],
+                    "operators": [
+                        {
+                          "opcode_index": 0,
+                          "inputs": [ 0 ],
+                          "outputs": [ 1 ],
+                          "builtin_options_type": "LogSoftmaxOptions",
+                          "custom_options_format": "FLEXBUFFERS"
+                        }
+                    ],
+                } ],
+                "buffers" : [ {}, {} ]
+            }
+        )";
+        SetupSingleInputSingleOutput("inputTensor", "outputTensor");
+    }
+};
+
+TEST_CASE_FIXTURE(LogSoftmaxFixture, "ParseLogSoftmaxLite")
+{
+    RunTest<2, armnn::DataType::QAsymmU8>(0, { 0, 0, 100, 0, 0, 0, 0 }, { 0, 0, 255, 0, 0, 0, 0 });
+}
+
+}