Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
A library built for easier audio self-supervised training, downstream tasks evaluation
Wav2Keyword is keyword spotting(KWS) based on Wav2Vec 2.0. This model shows state-of-the-art in Speech commands dataset V1 and V2.
Classify audio with neural nets on embedded systems like the Raspberry Pi
Pytorch Reimplementation of DiffWave unconditional generation: a high quality waveform synthesizer.
Kaggle Competitions: TensorFlow Speech Recognition Challenge
Pytorch implementation of BiFSMN, IJCAI 2022
Attention-based model for keywords spotting
Speech command recognition DenseNet transfer learning from UrbanSound8k in keras tensorflow
Effective processing pipeline and advanced neural network architectures for small-footprint keyword spotting
Generalized Deep Multiset Canonical Correlation Analysis for Multiview Learning of Speech Representations
A Python-based application designed specifically for visually impaired users, enabling them to seamlessly send and receive emails using intuitive speech commands. This innovative solution enhances accessibility and independence by allowing users to manage their email communication effortlessly, utilizing voice recognition technology to ensure a us.
Audio Classification with AlexNet and Speech Commands dataset
Small footprint, standalone, zero dependency, offline keyword spotting (KWS) CLI tool.
Wake-Up Keyword Detection With End To End Deep Neural Networks
A Vocola 2 (DNS) extension for creating and editing mathematics (in LaTeX) by voice, using a ZOO interface (Zoomable Online Outliner) such as WorkFlowy or Dynalist.
Edge-deployable keyword spotter: INT8-quantized DS-CNN on Google Speech Commands, exported to ONNX, with fp32 vs INT8 benchmarks, a live mic demo, and a C++ inference harness.
Multi-class classification of speech command data. Dataset collected from kaggle speech recognition challenge and used pyTorch for implementation.
FPGA NPU on PYNQ-Z2 (Zynq-7020): 8×8 int8 output-stationary systolic GEMM + transformer glue. MNIST for fabric bring-up; Google Speech Commands robot commands as end-to-end embedded app.
Browser camera and voice interaction prototype with locally loaded models.
To associate your repository with the speech-commands topic, visit your repo's landing page and select "manage topics."
