sampling frequency independent convolution for MOS prediction

Evaluation framework for speech anonymizers

Interpretable anonymizer based on kNN-VC

SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)

Contrastive Language-Audio Pretraining

Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

Spark-TTS Inference Code

Official PyTorch implementation of BigVGAN (ICLR 2023)

FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

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

Zero-Shot Foreign Accent Conversion without a Native Reference

[ASRU 2023] Code of paper SALT: Distinguishable Speaker Anonymization Through Latent Space Transformation

A Singing Style Conversion Framework Based On Audio Infilling

Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'

Multi-lingual AudioCaps

Unified automatic quality assessment for speech, music, and sound.

List of speech synthesis papers.

Retrieval-Augmented MOS Prediction with Prior Knowledge Integration

Python wrapper for OpenJTalk

Foundational Models for State-of-the-Art Speech and Text Translation

Baseline Recipe for VoicePrivacy Challenge 2024: anonymization systems and evaluation software

Modified transcriptions of YODAS dataset

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Versatile Evaluation of Speech and Audio

Train no-reference speech quality estimators with multiple datasets via learned, per-dataset alignments.