Text-to-speech (TTS) processing
PulseAugur coverage of Text-to-speech (TTS) processing — every cluster mentioning Text-to-speech (TTS) processing across labs, papers, and developer communities, ranked by signal.
-
Activation steering enhances TTS emotion control and intelligibility
Two new research papers introduce "activation steering" as a method to control aspects of generated speech without retraining existing text-to-speech (TTS) models. The first paper, "SteerSpeech," focuses on controlling …
-
UR-BERT enables 495-language multilingual TTS systems
Researchers have developed UR-BERT, a novel text encoder designed to significantly expand the capabilities of massively multilingual text-to-speech (TTS) systems. Unlike traditional methods limited by grapheme-to-phonem…
-
AI speech technologies collection includes TTS, STT, and voice cloning
This Mastodon post compiles resources on AI speech technologies. It covers Text-to-Speech (TTS), Speech-to-Text (STT), voice synthesis, and voice cloning. The page serves as a collection of notes and links for further e…
-
New ParsVoice Corpus Boosts Persian TTS Capabilities
Researchers have introduced ParsVoice, a substantial new corpus of Persian speech and text data designed to advance text-to-speech (TTS) synthesis and other speech processing tasks for the Persian language. This dataset…
-
AI Speech Technologies: A curated collection of TTS, STT, and voice synthesis resources
This Mastodon post compiles resources on AI speech technologies, covering Text-to-Speech (TTS), Speech-to-Text (STT), and voice synthesis. It serves as a central hub for information on various aspects of AI-driven voice…