diff options
author | Kshitij Sisodia <kshitij.sisodia@arm.com> | 2021-12-24 11:05:11 +0000 |
---|---|---|
committer | Liam Barry <liam.barry@arm.com> | 2021-12-24 14:20:36 +0000 |
commit | 76a1580861210e0310db23acbc29e1064ae30ead (patch) | |
tree | f947145cffd944aa3724c90745fc0e9d8e2fb2f4 /Readme.md | |
parent | 871fcdc755173b9f7ecb8cf9dc8dc6306329958c (diff) | |
download | ml-embedded-evaluation-kit-76a1580861210e0310db23acbc29e1064ae30ead.tar.gz |
MLECO-2599: Replace DSCNN with MicroNet for KWS
Added SoftMax function to Mathutils to allow MicroNet
to output probability as it does not nativelu have this layer.
Minor refactoring to accommodate Softmax Calculations
Extensive renaming and updating of documentation and resource download script.
Added SoftMax function to Mathutils to allow MicroNet
to output probability.
Change-Id: I7cbbda1024d14b85c9ac1beea7ca8fbffd0b6eb5
Signed-off-by: Liam Barry <liam.barry@arm.com>
Diffstat (limited to 'Readme.md')
-rw-r--r-- | Readme.md | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -30,9 +30,9 @@ The example application at your disposal and the utilized models are listed in t | ML application | Description | Neural Network Model | | :----------------------------------: | :-----------------------------------------------------: | :----: | | [Image classification](./docs/use_cases/img_class.md) | Recognize the presence of objects in a given image | [Mobilenet V2](https://github.com/ARM-software/ML-zoo/tree/e0aa361b03c738047b9147d1a50e3f2dcb13dbcb/models/image_classification/mobilenet_v2_1.0_224/tflite_int8) | -| [Keyword spotting(KWS)](./docs/use_cases/kws.md) | Recognize the presence of a key word in a recording | [DS-CNN-L](https://github.com/ARM-software/ML-zoo/tree/68b5fbc77ed28e67b2efc915997ea4477c1d9d5b/models/keyword_spotting/ds_cnn_large/tflite_clustered_int8) | +| [Keyword spotting(KWS)](./docs/use_cases/kws.md) | Recognize the presence of a key word in a recording | [MicroNet](https://github.com/ARM-software/ML-zoo/tree/9f506fe52b39df545f0e6c5ff9223f671bc5ae00/models/keyword_spotting/micronet_medium/tflite_int8) | | [Automated Speech Recognition(ASR)](./docs/use_cases/asr.md) | Transcribe words in a recording | [Wav2Letter](https://github.com/ARM-software/ML-zoo/tree/1a92aa08c0de49a7304e0a7f3f59df6f4fd33ac8/models/speech_recognition/wav2letter/tflite_int8) | -| [KWS and ASR](./docs/use_cases/kws_asr.md) | Utilise Cortex-M and Ethos-U to transcribe words in a recording after a keyword was spotted | [DS-CNN-L](https://github.com/ARM-software/ML-zoo/tree/68b5fbc77ed28e67b2efc915997ea4477c1d9d5b/models/keyword_spotting/ds_cnn_large/tflite_clustered_int8) [Wav2Letter](https://github.com/ARM-software/ML-zoo/tree/1a92aa08c0de49a7304e0a7f3f59df6f4fd33ac8/models/speech_recognition/wav2letter/tflite_int8) | +| [KWS and ASR](./docs/use_cases/kws_asr.md) | Utilise Cortex-M and Ethos-U to transcribe words in a recording after a keyword was spotted | [MicroNet](https://github.com/ARM-software/ML-zoo/tree/9f506fe52b39df545f0e6c5ff9223f671bc5ae00/models/keyword_spotting/micronet_medium/tflite_int8) [Wav2Letter](https://github.com/ARM-software/ML-zoo/tree/1a92aa08c0de49a7304e0a7f3f59df6f4fd33ac8/models/speech_recognition/wav2letter/tflite_int8) | | [Anomaly Detection](./docs/use_cases/ad.md) | Detecting abnormal behavior based on a sound recording of a machine | [MicroNet](https://github.com/ARM-software/ML-zoo/tree/7c32b097f7d94aae2cd0b98a8ed5a3ba81e66b18/models/anomaly_detection/micronet_medium/tflite_int8/)| | [Visual Wake Word](./docs/use_cases/visual_wake_word.md) | Recognize if person is present in a given image | [MicroNet](https://github.com/ARM-software/ML-zoo/tree/7dd3b16bb84007daf88be8648983c07f3eb21140/models/visual_wake_words/micronet_vww4/tflite_int8/vww4_128_128_INT8.tflite)| | [Noise Reduction](./docs/use_cases/noise_reduction.md) | Remove noise from audio while keeping speech intact | [RNNoise](https://github.com/ARM-software/ML-zoo/raw/a061600058097a2785d6f1f7785e5a2d2a142955/models/noise_suppression/RNNoise/tflite_int8) | |