DeepSpectrum / DeepSpectrumLite
Light-weight transfer learning framework for on-device speech and audio recognition using pre-trained image convolutional neural networks.
☆18Updated 2 years ago
Related projects: ⓘ
- Streaming Audiotransformers for online Audio tagging☆39Updated 3 months ago
- Improving Recording Device Generalization using Impulse Response Augmentation☆10Updated last year
- This is the official repository of the papers "Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers" and "Efficient Fi…☆33Updated last month
- ☆26Updated last year
- Learning differentiable temporal resolution on time-series data.☆33Updated last year
- (Hybrid) BYOL-S feature extractor using serab-byols package in pytorch.☆26Updated 5 months ago
- The Pytorch implementation of paper: Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training☆39Updated last year
- A probabilistic scoring backend for length-normalized embeddings.☆10Updated 4 months ago
- Towards Intelligibility-Oriented Audio-Visual Speech Enhancement☆13Updated 2 weeks ago
- VoViT: Low Latency Graph-based Audio-Visual VoiceSeparation Transformer☆33Updated last year
- Adapting a ConvNeXt model to audio classification on AudioSet☆17Updated 11 months ago
- Official implementation of EfficientLEAF, a learnable audio frontend.☆39Updated last year
- SERAB: a multi-lingual benchmark for speech emotion recognition☆28Updated last year
- A Pytorch implementation of the paper : SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification☆31Updated 3 years ago
- FastAudio is a Learnable Audio Frontend team Magnum's designed for the ASVspoof 2021 challenge☆42Updated last year
- ☆22Updated 2 years ago
- ☆13Updated last year
- Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model☆26Updated last year
- Python toolkit for likelihood-ratio calibration of binary classifiers☆23Updated last year
- Code for the paper: "Leveraging speaker attribute information using multi task learning for speaker verification and diarization" present…☆24Updated last year
- CDER (Conversational Diarization Error Rate) Scoring Tool☆15Updated 2 years ago
- Source code for ICASSP2022 "Pseudo Strong labels for large scale weakly supervised audio tagging"☆30Updated 2 years ago
- ☆23Updated last year
- SAMO: SPEAKER ATTRACTOR MULTI-CENTER ONE-CLASS LEARNING FOR VOICE ANTI-SPOOFING☆31Updated last year
- System that ranks 2nd in DCASE 2022 Challenge Task 5: Few-shot Bioacoustic Event Detection☆27Updated 2 years ago
- Masked Modeling Duo: Towards a Universal Audio Pre-training Framework☆63Updated last month
- A new comprehensive and diverse few-shot acoustic classification benchmark.☆58Updated 3 months ago
- Balanced Error Rate for Speaker Diarization☆25Updated last year
- ☆27Updated 5 months ago
- ☆24Updated last year