Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep neural networks for getting text-independent speaker embedding written in TensorFlow
| Date | Stars |
|---|---|
| 2026-07-31 | 310 |
| 2026-08-03 | 310 |
| 2026-08-04 | 310 |
| 2026-08-06 | 310 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Text-independent voice vectors ## Subtitle: which of the Hollywood stars is most similar to my voice? >* Authors: Dabi Ahn([email protected]), [Noah Jung](https://github.com/giallo41), [Jujin Lee](https://github.com/zeze-zzz) and [Kyubyong Park](https://github.com/Kyubyong) >* [Demo: Check out who your voice is like!](https://voice-vector-web.andabi.me/) ## Prologue Everyone has their own voice. The same voice will not exist from different people, but some people have similar voices while others do not. This project aims to find individual voice vectors using [VoxCeleb](http://www.robots.ox.ac.uk/~vgg/data/voxceleb) dataset, which contains 1,251 Hollywood stars' 145,379 utterances. The voice vectors are text-independent, meaning that any pair of utterances from same speaker has similar voice vectors. Also the closer the vector distance is, the more voices are similar. <p align="center"><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/title.png" width="60%"></p> ## Architectures The architecture is based on a classification model. The utterance inputted is classified as one of the Hollywood stars. The objective function is simply a cross entropy between speaker labels from ground truth and predictions. Eventually, the last layer's activation becomes the speaker's embedding. The model architecture is structured as follows. 1. memory cell * CBHG module from [Tacotron](https://arxiv.org/abs/1703.10135) captures hidden features from sequential data. 2. embedding * memory cell's last output is projected by the size of embedding vector. 3. softmax * embedding is logits for each classes. <p align="center"><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/arch.png" width="100%"></p> ## Training * [VoxCeleb](http://www.robots.ox.ac.uk/~vgg/data/voxceleb) dataset used. * 1,251 Hollywood stars' 145,379 utterances * gender dist.: 690 males and 561 females * age dist.: 136, 351, 318, 210, and 236 for 20s, 30s, 40s, 50s, and over 60s respectively. * text-independent * at each step, the speaker is arbitrarily selected. * for each speaker, the utterance inputted is randomly selected and cropped so that it does not matter to text. * loss and train accuracy * <br><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/train_loss.png" width="40%"><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/train_acc.png" width="40%"> ## Embedding * [Common Voice](https://voice.mozilla.org/) dataset used for inference. * hundreds of thousands of English utterances from numerous voice contributors in the world. * evaluation accuracy * <br><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/eval_acc.png" width="40%"> * embedding visualization using t-SNE * voices are well clustered by gender without any supervision in training. * <p align="center"><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/embed_gender.png" width="100%"></p> * but we could not find any tendency toward age. * <p align="center"><img src="https://raw.githubusercontent.com/andabi/voice-vector/master/materials/embed_age.png" width="100%"></p> ## How to run? ### Requirements * python 2.7 * tensorflow >= 1.1 * numpy >= 1.11.1 * librosa == 0.5.1 * tensorpack == 0.8.0 ### Settings * configurations are set in two YAML files. * `hparams/default.yaml` includes default settings for signal processing, model, training, evaluation and embedding. * `hparams/hparams.yaml` is for customizing the default settings in each experiment case. ### Runnable python files * `train.py` for training. * run `python train.py some_case_name` * remote mode: utilizing more cores of remote server to load data and enqueue more quickly. * run `python train.py some_case_name -remote -port=1234` in local server. * run `python remote_dataflow.py some
Excerpt of 5,467 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9ef724cd35feb150, llm:Repository description: 'Deep neural networks for getting text-independent speaker embedding written in TensorFlow' (Python).
matched fp:9ef724cd35feb150, llm:Repository description: 'Deep neural networks for getting text-independent speaker embedding written in TensorFlow' (Python).