January 19, 2020

Comments

Developer Blog: How to Deploy Real-Time Text-to-Speech Applications on GPUs Using TensorRT

In this developer blog post, we’ll walk through how to convert a PyTorch model through ONNX intermediate representation to TensorRT 7 to speed up inference in one of the parts of Conversational AI – Speech Synthesis. … Read more

January 17, 2020

Comments

Nuance Accelerates Conversational AI Training by 50%

Using Automatic Mixed Precision running on TensorFlow, Nuance has realized a 50% speedup in ASR and NLP model training on NVIDIA Volta GPUs without loss of accuracy, helping to reduce their time to market. … Read more

September 16, 2019

Comments

NVIDIA Announces TensorRT 6; Breaks 10 millisecond barrier for BERT-Large

Today, NVIDIA released TensorRT 6 which includes new capabilities that dramatically accelerate conversational AI applications, speech recognition, 3D image segmentation for medical applications, as well as image-based applications in industrial automation. … Read more

August 29, 2019

Comments

Google Develops ASR System To Help People with Speech Impairments

Google researchers have developed a deep learning-based automatic speech recognition (ASR) system that aims to improve communications for people with amyotrophic lateral sclerosis (ALS) … Read more

August 13, 2019

Comments

NVIDIA Slashes BERT Training and Inference Times

In today’s announcement, researchers and developers from NVIDIA set records in both training and inference of BERT, one of the most popular AI language models. … Read more

July 1, 2019

Comments

Top 5 AI Speech Applications Using NVIDIA’s GPUs for Inference

To help developers manage growing datasets, latency requirements, customer requirements, and more complex neural networks, we are highlighting a few AI speech applications that rely on NVIDIA’s inference platform to solve common AI speech challenges. … Read more

June 28, 2019

Comments

New GAN Can Lipread and Synthesize Speech

Researchers from Samsung and Imperial College in London developed a deep learning solution that uses computer vision for visual speech recognition. … Read more

June 26, 2019

Comments

AI Model Can Generate Images from Natural Language Descriptions

Researchers from IBM and the University of Virginia developed a deep learning model that can generate objects and their attributes from natural language descriptions. … Read more

May 31, 2019

Comments

Amazon Improves Speech Emotion Detection with Adversarial Training Using NVIDIA GPUs

Developers from Amazon’s Alexa Research group have just published a developer blog and published a paper describing how they are using adversarial training to recognize and improve emotion detection. … Read more

May 29, 2019

Comments

Inception Spotlight: DeepZen Uses AI to Generate Speech for Audiobooks

DeepZen, a London-based company, and a member of NVIDIA's Inception program, developed a deep learning-based system that can generate complete audio recordings of books and other voice related applications that are human-like and filled with emotion. … Read more

Tag Archives: Speech & Audio Processing

Developer Blog: How to Deploy Real-Time Text-to-Speech Applications on GPUs Using TensorRT

Nuance Accelerates Conversational AI Training by 50%

NVIDIA Announces TensorRT 6; Breaks 10 millisecond barrier for BERT-Large

Google Develops ASR System To Help People with Speech Impairments

NVIDIA Slashes BERT Training and Inference Times

Top 5 AI Speech Applications Using NVIDIA’s GPUs for Inference

New GAN Can Lipread and Synthesize Speech

AI Model Can Generate Images from Natural Language Descriptions

Amazon Improves Speech Emotion Detection with Adversarial Training Using NVIDIA GPUs

GET STARTED

LEARN MORE

GET INVOLVED