Date / Heure
Date(s) - 04/06/2019
12h30 - 14h30

Emplacement
Algolia 55 Rue d'Amsterdam Algolia 55 Rue d'Amsterdam · Paris

Catégories

Today we’ll have a peer-to-peer discussion about new advances in speech generation techniques including software libraries and cloud services.

Tuesdays are applied machine learning day. We have a peer-to-peer discussion with a focus on an applied machine learning topic. We also meet on Fridays when we discuss a predetermined research paper.

Bring lunch and, if you wish, a research paper, some questions, a demo, a problem, or just come to hang out.

Resources (Will be frequently updated):

1. FastSpeech: Fast, Robust and Controllable
Text to Speech: https://arxiv.org/abs/1905.09263v2

2. Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System: https://arxiv.org/abs/1905.01641v1

3. Speech Devices SDK Microphone array recommendations: https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-devices-sdk-microphone

4. Direct speech-to-speech translation with a sequence-to-sequence model (Google Translatotron): https://arxiv.org/abs/1904.06037v1

5. Almost Unsupervised Text to Speech and Automatic Speech Recognition (Microsoft): https://arxiv.org/abs/1905.06791

Previously Studied Papers:

1. Tacotron: Towards End-to-End Speech Synthesis: https://arxiv.org/abs/1703.10135v2

Use Cases:

1. Political Speech Generation: https://arxiv.org/abs/1601.03313v2

https://www.meetup.com/fr-FR/Paris-Machine-Learning-Study-Group-in-English-Meetup/events/qzcnzqyzjbgb/