Code for ACL 2019 Paper: "COMET: Commonsense Transformers for Automatic Knowledge Graph Construction" https://arxiv.org/abs/1906.05317

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Implementation of Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt (NAACL'24).

Crowdsourced and Automatic Speech Prominence Estimation

Facestar dataset. High quality audio-visual recordings of human conversational speech.

Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Official implementation for the paper Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

MARS5 speech model (TTS) from CAMB.AI

Use OpenAI's realtime API for a chatting with your documents

A simple, high-quality voice conversion tool focused on ease of use and performance.

Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning

[ICASSP 2024] KNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

ChatReviewer: 使用ChatGPT分析论文优缺点，提出改进建议

Code for Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction (ACL24))

A comprehensive overview of affective computing research in the era of large language models (LLMs).

SpeechGPT Series: Speech Large Language Models

Code for InterSpeech 2024 Paper: LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition

The source code for the paper titled "Sentiment Knowledge Enhanced Attention Fusion Network (SKEAFN)".

[ICASSP2024] Code for paper "SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection"

SiLLM is a Simultaneous Machine Translation (SiMT) Framework. It utilizes a Large Language model as the translation model and employs a traditional SiMT model for policy-decision to achieve SiMT th…

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Multi-Task Speech classification of accent and gender of an english speaker on Mozilla's common voice dataset

Official release of InternLM2.5 base and chat models. 1M context support

Reliable Conflictive Multi-view Learning

Source code for the paper 'Audio Captioning Transformer'