# ts-audio

**Repository Path**: WTBU_CS/ts-audio

## Basic Information

- **Project Name**: ts-audio
- **Description**: 包含11个语音算法，其内容丰富，涵盖了智能语音下的语音识别、说话人识别、语音转换、语音分离、语音情感识别等多个领域。这些算法上手较简单，易于部署和训练，便于开发者使用。此外，其中的Speaker_Verification_GE2Eloss等算法的精度高于论文精度，具有较高的研究价值。
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 8
- **Created**: 2024-06-18
- **Last Updated**: 2024-06-18

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# ts-audio

包含22个语音算法，其内容丰富，涵盖了智能语音下的语音识别、声纹识别、语音分类、语音情感识别、语音合成等多个领域。这些算法上手较简单，易于部署和训练，便于开发者使用。此外，其中的Speaker_Verification_GE2Eloss等算法的精度高于论文精度，具有较高的研究价值。

## **声纹识别**

[Speaker_Verification_GE2Eloss](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Speaker_Verification_GE2Eloss)

[oneflow-sincnet](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/SincNet)

[oneflow-am-mobilenet-1d](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/AM-MobileNet1D)

## **音色转换**

[CycleGan-VC2](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/CycleGAN-VC2)

[StarGAN-VC](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/StarGAN-VC)

[Adaptive_Voice_Conversion  ](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Adaptive_Voice_Conversion)

[MaskCycleGAN-VC](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/MaskCycleGAN-VC)

## **语音识别**

[Speech_Transformer](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Speech-Transformer)

[oneflow_wav2letter](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Wav2Letter)

[Listen-Attend-Spell](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Listen-Attend-Spell)

[DeepSpeech2](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/DeepSpeech2)

[JointTransformerAndCTC](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/JointTransformerAndCTC)

[NART](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/NART)

[OpenTransformer](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/OpenTransformer)

[Transducer](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Transducer_Oneflow)

## **语音分离**

[Conv-TasNet](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Conv-TasNet)

## **语音情感识别**

[Speech-Emotion-Analyzer](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Speech-Emotion-Analyzer)

[Speech-Emotion-Classification](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Speech-Emotion-Classification-with-oneflow)

[VoiceEmotionAnalysis](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/VoiceEmotionAnalysis)

## **语音合成**

[ParallelWaveGAN](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/ParallelWaveGAN)

[Transformer-TTS](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/Transformer-TTS)

[wavenet](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/wavenet_vocoder_oneflow)

## **语音分类**

[AudioClassification](https://gitee.com/zhijiangtianshu/ts-audio/tree/master/AudioClassification)