Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,59 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- Cnam-LMSSC/vibravox
|
5 |
+
language:
|
6 |
+
- fr
|
7 |
+
---
|
8 |
+
# Master Model Card: Vibravox Audio Bandwidth extension Models
|
9 |
+
|
10 |
+
<p align="center">
|
11 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6390fc80e6d656eb421bab69/KkZoQQmrn53U6BTLmr0XK.png" />
|
12 |
+
</p>
|
13 |
+
|
14 |
+
## Overview
|
15 |
+
|
16 |
+
This master model card serves as an entry point for exploring multiple **audio bandwidth extension** (BWE) models trained on different sensor data from the [Vibravox dataset](https://huggingface.co/datasets/Cnam-LMSSC/vibravox).
|
17 |
+
|
18 |
+
These models are designed to to enhance the audio quality of body-conducted captured speech, by denoising and regenerating mid and high frequencies from low frequency content only.
|
19 |
+
|
20 |
+
The models are trained on specific sensors to address various audio capture scenarios using **body conducted** sound and vibration sensors.
|
21 |
+
|
22 |
+
## Disclaimer
|
23 |
+
Each of these models has been trained for **specific non-conventional speech sensors** and is intended to be used with **in-domain data**.
|
24 |
+
|
25 |
+
Please be advised that using these models outside their intended sensor data may result in suboptimal performance.
|
26 |
+
|
27 |
+
## Usage
|
28 |
+
All models are trained using [Configurable EBEN](https://github.com/jhauret/vibravox/blob/main/vibravox/torch_modules/dnn/eben_generator.py) (see [publication](https://ieeexplore.ieee.org/document/10244161)) and adapted to different sensor inputs. They are intended to be used at a sample rate of 16kHz.
|
29 |
+
|
30 |
+
## Training Procedure
|
31 |
+
Detailed instructions for reproducing the experiments are available on the [jhauret/vibravox](https://github.com/jhauret/vibravox) Github repository.
|
32 |
+
|
33 |
+
## Available Models
|
34 |
+
|
35 |
+
The following models are available, **each trained on a different sensor** from the (https://huggingface.co/datasets/Cnam-LMSSC/vibravox):
|
36 |
+
|
37 |
+
| **Transducer** | **Huggingface model link** | **Training dataset** |
|
38 |
+
|:---------------------------|:---------------------|:-------------|
|
39 |
+
| In-ear comply foam-embedded microphone |[EBEN BWE Model for in-ear comply foam-embedded microphone](https://huggingface.co/Cnam-LMSSC/EBEN_bwe_soft_in_ear_mic) | `speech_clean` subset of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) |
|
40 |
+
| In-ear rigid earpiece-embedded microphone | [EBEN BWE Model for in-ear rigid earpiece-embedded microphone](https://huggingface.co/Cnam-LMSSC/EBEN_bwe_rigid_in_ear_mic) | `speech_clean` subset of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) |
|
41 |
+
| Forehead miniature vibration sensor | [EBEN BWE Model for forehead vibration sensor](https://huggingface.co/Cnam-LMSSC/EBEN_bwe_forehead_accelerometer) | `speech_clean` subset of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) |
|
42 |
+
| Temple vibration pickup | [EBEN BWE Model for temple vibration pickup](https://huggingface.co/Cnam-LMSSC/EBEN_bwe_temple_vibration_pickup) | `speech_clean` subset of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) |
|
43 |
+
| Laryngophone | [EBEN BWE Model for laryngophone](https://huggingface.co/Cnam-LMSSC/EBEN_bwe_phonemizer_laryngophone) | `speech_clean` subset of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) |
|
44 |
+
|
45 |
+
|
46 |
+
## License
|
47 |
+
All these models are released under the MIT License.
|
48 |
+
|
49 |
+
|
50 |
+
## Sensors positioning and documentation
|
51 |
+
|
52 |
+
|
53 |
+
| **Sensor** | **Image** | **Transducer** | **Online documentation** |
|
54 |
+
|:---------------------------|:---------------------|:-------------|:----------------------------------------------------------------------------------------------------------------------|
|
55 |
+
| In-ear comply foam-embedded microphone |![image/png](https://cdn-uploads.huggingface.co/production/uploads/65302a613ecbe51d6a6ddcec/OJ4TGk-aH6M0jRUJVdA2B.png)| Knowles FG-23329-P07 | [See documentation on vibravox.cnam.fr](https://vibravox.cnam.fr/documentation/hardware/microphones/soft_inear/index.html) |
|
56 |
+
| In-ear rigid earpiece-embedded microphone | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65302a613ecbe51d6a6ddcec/DIuuYaTk7Ba67CsJlplmZ.png) | Knowles SPH1642HT5H | [See documentation on vibravox.cnam.fr](https://vibravox.cnam.fr/documentation/hardware/microphones/rigid_inear/index.html) |
|
57 |
+
| Forehead miniature vibration sensor | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65302a613ecbe51d6a6ddcec/ttdc4Bakbf6O3KxNoNERW.png) | Knowles BU23173-000 | [See documentation on vibravox.cnam.fr](https://vibravox.cnam.fr/documentation/hardware/microphones/forehead/index.html) |
|
58 |
+
| Temple vibration pickup | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65302a613ecbe51d6a6ddcec/uHZ2mhHAlCmd0e_jdESK6.png) | AKG C411 | [See documentation on vibravox.cnam.fr](https://vibravox.cnam.fr/documentation/hardware/microphones/temple/index.html) |
|
59 |
+
| Laryngophone | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65302a613ecbe51d6a6ddcec/KaS7sxV4g4JOSB3ERKnha.png) | iXRadio XVTM822D-D35 | [See documentation on vibravox.cnam.fr](https://vibravox.cnam.fr/documentation/hardware/microphones/throat/index.html) |
|