| OLD | NEW |
| 1 # APM Quality Assessment tool | 1 # APM Quality Assessment tool |
| 2 | 2 |
| 3 Python wrapper of `audioproc_f` with which quality assessment can be | 3 Python wrapper of `audioproc_f` with which quality assessment can be |
| 4 automatized. The tool allows to simulate different noise conditions, input | 4 automatized. The tool allows to simulate different noise conditions, input |
| 5 signals, APM configurations and it computes different scores. | 5 signals, APM configurations and it computes different scores. |
| 6 Once the scores are computed, the results can be easily exported to an HTML page | 6 Once the scores are computed, the results can be easily exported to an HTML page |
| 7 which allows to listen to the APM input and output signals and also the | 7 which allows to listen to the APM input and output signals and also the |
| 8 reference one used for evaluation. | 8 reference one used for evaluation. |
| 9 | 9 |
| 10 ## Dependencies | 10 ## Dependencies |
| (...skipping 15 matching lines...) Expand all Loading... |
| 26 - Aachen Impulse Response (AIR) Database | 26 - Aachen Impulse Response (AIR) Database |
| 27 - Download https://www2.iks.rwth-aachen.de/air/air_database_release_1_4.zip | 27 - Download https://www2.iks.rwth-aachen.de/air/air_database_release_1_4.zip |
| 28 - Input probing signals and noise tracks (you can make your own dataset - *1) | 28 - Input probing signals and noise tracks (you can make your own dataset - *1) |
| 29 | 29 |
| 30 ## Build | 30 ## Build |
| 31 | 31 |
| 32 - Compile WebRTC | 32 - Compile WebRTC |
| 33 - Go to `out/Default/py_quality_assessment` and check that | 33 - Go to `out/Default/py_quality_assessment` and check that |
| 34 `apm_quality_assessment.py` exists | 34 `apm_quality_assessment.py` exists |
| 35 | 35 |
| 36 ## Unit tests |
| 37 |
| 38 - Compile WebRTC |
| 39 - Go to `out/Default/py_quality_assessment` |
| 40 - Run `python -m unittest -p "*_unittest.py" discover` |
| 41 |
| 36 ## First time setup | 42 ## First time setup |
| 37 | 43 |
| 38 - Deploy PolqaOem64 and set the `POLQA_PATH` environment variable | 44 - Deploy PolqaOem64 and set the `POLQA_PATH` environment variable |
| 39 - e.g., `$ export POLQA_PATH=/var/opt/PolqaOem64` | 45 - e.g., `$ export POLQA_PATH=/var/opt/PolqaOem64` |
| 40 - Deploy the AIR Database and set the `AECHEN_IR_DATABASE_PATH` environment | 46 - Deploy the AIR Database and set the `AECHEN_IR_DATABASE_PATH` environment |
| 41 variable | 47 variable |
| 42 - e.g., `$ export AECHEN_IR_DATABASE_PATH=/var/opt/AIR_1_4` | 48 - e.g., `$ export AECHEN_IR_DATABASE_PATH=/var/opt/AIR_1_4` |
| 43 - Deploy probing signal tracks into | 49 - Deploy probing signal tracks into |
| 44 - `out/Default/py_quality_assessment/probing_signals` (*1) | 50 - `out/Default/py_quality_assessment/probing_signals` (*1) |
| 45 - Deploy noise tracks into | 51 - Deploy noise tracks into |
| (...skipping 54 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
| 100 Depending on the license, the POLQA tool may take “breaks” as a way to limit the | 106 Depending on the license, the POLQA tool may take “breaks” as a way to limit the |
| 101 throughput. When this happens, the APM Quality Assessment tool is slowed down. | 107 throughput. When this happens, the APM Quality Assessment tool is slowed down. |
| 102 For more details about this limitation, check Section 10.9.1 in the POLQA manual | 108 For more details about this limitation, check Section 10.9.1 in the POLQA manual |
| 103 v.1.18. | 109 v.1.18. |
| 104 | 110 |
| 105 In case of issues with the POLQA score computation, check | 111 In case of issues with the POLQA score computation, check |
| 106 `py_quality_assessment/eval_scores.py` and adapt | 112 `py_quality_assessment/eval_scores.py` and adapt |
| 107 `PolqaScore._parse_output_file()`. | 113 `PolqaScore._parse_output_file()`. |
| 108 The code can be also fixed directly into the build directory (namely, | 114 The code can be also fixed directly into the build directory (namely, |
| 109 `out/Default/py_quality_assessment/eval_scores.py`). | 115 `out/Default/py_quality_assessment/eval_scores.py`). |
| OLD | NEW |