metadata

language: fr
license: mit
library_name: transformers
tags:
  - audio
  - audio-to-audio
  - speech
datasets:
  - Cnam-LMSSC/vibravox
model-index:
  - name: EBEN(M=4,P=4,Q=4)
    results:
      - task:
          name: Bandwidth Extension
          type: speech-enhancement
        dataset:
          name: >-
            Vibravox["headset_microphone"] to
            Vibravox["temple_vibration_pickup"]
          type: Cnam-LMSSC/vibravox
          args: fr
        metrics:
          - name: Test STOI, in-domain training
            type: stoi
            value: 0.4351

Model Card

Developed by: Cnam-LMSSC
Model: EBEN(M=4,P=4,Q=4) (see publication in IEEE TASLP - arXiv link)
Language: French
License: MIT
Training dataset: speech_clean subset of Cnam-LMSSC/vibravox
Samplerate for usage: 16kHz

Overview

This model, trained on Vibravox body conduction sensor data, maps clean speech to body-conducted speech.

Inference script :

import torch, torchaudio
from vibravox.torch_modules.dnn.eben_generator import EBENGenerator
from datasets import load_dataset

model = EBENGenerator.from_pretrained("Cnam-LMSSC/EBEN_reverse_temple_vibration_pickup")
test_dataset = load_dataset("Cnam-LMSSC/vibravox", "speech_clean", split="test", streaming=True)

audio_48kHz = torch.Tensor(next(iter(test_dataset))["audio.headset_microphone"]["array"])
audio_16kHz = torchaudio.functional.resample(audio_48kHz, orig_freq=48_000, new_freq=16_000)

cut_audio_16kHz = model.cut_to_valid_length(audio_16kHz[None, None, :])
degraded_audio_16kHz, _ = model(cut_audio_16kHz)