This class is designed to apply a very primitive decoding model on top of the instantaneous results from running an audio recognition model on a single window of samples. It applies smoothing over time so that noisy individual label scores are averaged, increasing the confidence that apparent matches are real. To use it, you should create a class object with the configuration you want, and then feed results from running a TensorFlow model into the processing method. The timestamp for each subsequent call should be increasing from the previous, since the class is designed to process a stream of data over time. More...
#include <TfLiteAudioStream.h>
Classes | |
| struct | Result |
Public Member Functions | |
| bool | begin (TfLiteConfig cfg) override |
| Setup parameters from config. | |
| virtual TfLiteStatus | getCommand (const TfLiteTensor *latest_results, const int32_t current_time_ms, const char **found_command, uint8_t *score, bool *is_new_command) override |
Protected Member Functions | |
| int | categoryCount () |
| Determines the number of categories. | |
| void | deleteOldRecords (int32_t limit) |
| Removes obsolete records from the queue. | |
| TfLiteStatus | evaluate (const char **found_command, uint8_t *result_score, bool *is_new_command) |
| Finds the result. | |
| int | resultCategoryIdx (int8_t *score) |
| finds the category with the biggest score | |
| TfLiteStatus | validate (const TfLiteTensor *latest_results) |
| Checks the input data. | |
Protected Attributes | |
| TfLiteConfig | cfg |
| int32_t | current_time_ms =0 |
| int | previous_cateogory =-1 |
| int32_t | previous_time_ms =0 |
| Vector< Result > | result_queue |
| int32_t | time_since_last_top =0 |
Detailed Description
This class is designed to apply a very primitive decoding model on top of the instantaneous results from running an audio recognition model on a single window of samples. It applies smoothing over time so that noisy individual label scores are averaged, increasing the confidence that apparent matches are real. To use it, you should create a class object with the configuration you want, and then feed results from running a TensorFlow model into the processing method. The timestamp for each subsequent call should be increasing from the previous, since the class is designed to process a stream of data over time.
The documentation for this class was generated from the following file:
- src/AudioLibs/TfLiteAudioStream.h
