Tag: text-to-speech

AI / Deep Learning

Creating Voice-based Virtual Assistants Using NVIDIA Riva and Rasa

Virtual assistants have become part of our daily lives. We ask Siri almost anything that we wonder about or order groceries through Alexa. 16 MIN READ
AI / Deep Learning

Speeding Up Development of Speech and Language Models with NVIDIA NeMo

As a researcher building state-of-the-art speech and language models, you must be able to quickly experiment with novel network architectures. 7 MIN READ
AI / Deep Learning

Training Your Own Voice Font Using Flowtron

Recent conversational AI research has demonstrated automatically generating high quality, human-like audio from text. For example, you can use Tacotron 2 and… 12 MIN READ
AI / Deep Learning

Creating Robust Neural Speech Synthesis with ForwardTacotron

Photo by Thomas Le: The artificial production of human speech, also known as speech synthesis, has always been a fascinating… 10 MIN READ
AI / Deep Learning

Building a Simple AI Assistant with DeepPavlov and NVIDIA NeMo

In the past few years, voice-based interaction has become a feature of many industrial products. Voice platforms like Amazon Alexa, Google Home, Xiaomi Xiaz… 10 MIN READ
AI / Deep Learning

Getting a Real Time Factor Over 60 for Text-To-Speech Services Using NVIDIA Riva

Figure 1. Riva Server and the TTS pipeline. NVIDIA Riva is an application framework that provides several pipelines for accomplishing conversational AI tasks. 19 MIN READ