Join us for an engaging online conversation with experts from Google, Meta, NVIDIA, and more on trends and techniques in automatic speech recognition (ASR) and text-to-speech (TTS) technologies.
Speech AI is becoming ubiquitous, helping businesses around the world power virtual assistants, scale call centers, take meeting notes, enhance AR experiences, and more. During the summit, you’ll hear from speech AI leaders on their latest work - research, production, and open source - to make speech AI more accurate, engaging, and globally accessible.
Research Associate at NYU Abu Dhabi | YouTube Educator
TTS Deep Learning Engineer | Coqui.ai
SVP, Technical and Field Operations| FOX Sports
Product Manager, Data Strategy - Riva | NVIDIA
Product Lead, Mozilla Foundation | Common Voice
Research Scientist in FAIR | Meta
Principal Research Scientist | Google
Practice Lead, NEXT Product & Platforms, Next Gen Tech | NCS
Director of XR | NVIDIA
9:00 – 9:45 a.m. PT
Voice-enabled technology is becoming ubiquitous. But many are being left behind by an anglocentric and demographically biased algorithmic world. Mozilla Common Voice and NVIDIA are collaborating to change that. By partnering on a public crowdsourced multilingual speech corpus - now the largest of its kinds in the world - and open source pre-trained models, we are making it easier than ever before to build Automatic Speech Recognition that works for speakers of the world's many languages.
10:00 – 10:45 a.m. PT
Text-to-Speech (TTS) systems have significantly advanced in recent years with deep learning approaches, these advances have motivated research that aims to synthesize speech into the voice of a target speaker using just a few seconds of speech. This approach is called Zero-Shot Multi-speaker TTS. In this talk, we will explore the timeline and the state-of-the-art on this task.
11:00 – 11:45 a.m. PT
Speech representation learning approaches achieved a groundbreaking performance in low-resource, multilingual, and audio-visual speech recognition. Furthermore, they opened the door for a new Textless NLP research direction that harnesses rich nonverbal information in human interaction missing in pretraining text resources and facilitates working with languages and dialects without standard orthography. This talk highlights work on both directions, connect them, and discusses future directions.
12:00 - 12:45 p.m. PT
End-to-end (E2E) speech recognition has become a popular research paradigm in recent years, allowing the modular components of a conventional speech recognition system (acoustic model, pronunciation model, language model), to be replaced by one neural network. In this talk, we will discuss a multi-year research journey of E2E modeling for speech recognition at Google. This journey has resulted in E2E models that can surpass the performance of conventional models across many different quality and latency metrics, as well as the productionization of E2E models for Pixel 4, 5 and 6 phones. We will also touch upon future research efforts with E2E models, including multi-lingual speech recognition.
1:00 – 1:45 p.m. PT
Hear from industry leaders about new interesting applications of speech AI in industry as well as challenges, tips, and emerging trends.
Explore the fundamentals of ASR and TTS and how they are used in various industries.
Get an overview of the important terminologies in the world of speech AI.
Dive into real-life speech AI use cases for contact center, video conferencing, and more.
Try NVIDIA® Riva’s interactive ASR and TTS demos to see, in real time, how Riva delivers highly accurate transcription and natural-sounding, expressive voices.
Sign up to receive the latest speech AI news from NVIDIA