IEEE

An Automated Method to Correct Artifacts in Neural Text-to-Speech Models

Abstract: Recent advances in deep learning technology have enabled high-quality speech synthesis, and text-to-speech models are widely used in a variety of applications. However, even state-of-the-art ...
GitHub

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

Small and fast: only 123M parameters. High-quality voice cloning: state-of-the-art performance in speaker similarity, intelligibility, and naturalness. Multi-lingual: support Chinese and English.
Reuters

Not all computer code protected as speech, US appeals court finds in ghost gun case

Court rules not all computer code is protected under First Amendment's free speech shield Gun website loses bid to revive lawsuit over ghost gun code Lawsuit followed New Jersey crackdown on ghost ...
Reuters

Cadence introduces an AI agent to speed up computer chip design

WASHINGTON, Feb 10 (Reuters) - Cadence Design Systems on Tuesday rolled out a virtual artificial intelligence "agent" to help firms like Nvidia speed up the complex process of designing computer chips ...
IEEE

Aligning Speech-Text Representations via Contrastive Modality Translation

Abstract: Recent advances in automatic speech recognition (ASR) have led to substantial improvements in system accuracy and robustness, particularly in converting speech signals into text sequences.