Technical Blog
Tag: Speech & Audio Processing
Subscribe
Technical Walkthrough
Sep 21, 2021
Transforming Noisy Low-Resolution into High-Quality Videos for Captivating End-User Experiences
The NVIDIA Maxine Video Effects SDK offers AI-based visual features that transform noisy, low-resolution video streams into pleasant user experiences.
16 MIN READ
Technical Walkthrough
Sep 21, 2021
Achieving Noise-Free Audio for Virtual Collaboration and Content Creation Applications
The Maxine Audio Effects SDK enables applications that integrate features such as noise removal and room echo removal.
11 MIN READ
News
Aug 30, 2021
Inception Spotlight: Supercharging Synthetic Speech with Resemble AI
This NVIDIA Inception Spotlight features Resemble AI, a new generative voice technology startup able to create high-quality synthetic AI voices.
2 MIN READ
Technical Walkthrough
May 24, 2021
Generating High-Quality Labels for Speech Recognition with Label Studio and NVIDIA NeMo
Save time and produce a more accurate result when processing audio data with automated speech recognition (ASR) models from NVIDIA NeMo and Label Studio.
6 MIN READ
News
Nov 18, 2020
Inception Spotlight: Watch Deepgram Transcribe 10 Hours of Audio in Just 40 Seconds using GPUs
Deepgram, a company developing automatic speech recognition (ASR) deep learning models, recently published a new demo that highlights the speed and scalability of its platform on NVIDIA GPUs.
< 1
News
Oct 20, 2020
Facebook AI Model Translates Between 100 Languages Without English Data
Facebook AI recently announced they are open sourcing a deep learning model called M2M-100 that can translate any language pair, among 100 languages, without relying on English data.
2 MIN READ