Amphion Team

Popular repositories Loading

1. Emilia-NV Emilia-NV Public

   Official Repository of Paper: "Emilia-NV: A Non-Verbal Speech Dataset with Word-Level Annotation for Human-Like Speech Modeling"

   96 3

2. SpeechJudge SpeechJudge Public

   SpeechJudge: Towards Human-Level Judgment for Speech Naturalness (https://arxiv.org/abs/2511.07931)

   Python 85 4

3. TaDiCodec TaDiCodec Public

   This repository contains a series of works on diffusion-based speech tokenizers, including the official implementation of the paper: "TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Lan…

   Python 79 3

4. SD-Eval SD-Eval Public

   [NeurIPS 2024] SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words

   Python 57 2

5. FlexiCodec FlexiCodec Public

   [ICLR2026] FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates

   Python 54 6

6. AnyAccomp AnyAccomp Public

   AnyAccomp: Generalizable accompaniment generation for vocals and solo instruments, powered by a quantized melodic bottleneck.

   Python 40 3