Speech AI Summit

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. 

EM Lewis-Jong, Product Lead, Mozilla Foundation | Common Voice

Caroline de Brito Gottlieb, Product Manager, Data Strategy - Riva | NVIDIA

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. 

Edresson Casanova, TTS Deep Learning Engineer | Coqui.ai

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. 

Abdelrahman Mohamed, Research Scientist in FAIR | Meta

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. 

Tara Sainath, Principal Research Scientist | Google

Hear from industry leaders about new interesting applications of speech AI in industry as well as challenges, tips, and emerging trends.

Michael Davies, SVP, Technical and Field Operations| FOX Sports

Dr. Sunil Sivadas, Practice Lead, NEXT Product & Platforms, Next Gen Tech | NCS

David Weinstein, Director of XR | NVIDIA

Moderated by Dr. Ahmad Bazzi, Research Associate at NYU Abu Dhabi | YouTube Educator