Papercup Engineering Blog

Highlights of INTERSPEECH 2020

First off, the organisers of INTERSPEECH 2020 have really outdone themselves with the first ever, fully remote INTERSPEECH this year. Of course, we all would have loved…

machine learning text to speech reinforcement learning

Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learning

(Paper, Samples) Efforts towards incremental text to speech (TTS) systems have largely focused on traditional, non-neural architectures . As samples from neural TTS…

machine learning phonological features 0-shot TTS

Phonological Features for 0-shot Multilingual Speech Synthesis

So far, code-switching is only available in multilingual models When working with video in multiple languages, something we often have to deal with is a phenomenon…

machine learning productionisation software engineering ml practices ml processes

Productionising machine learning through the lens of semiconductor fabrication

(Photo from Unsplash) Current machine learning processes leave much to be desired A persistent criticism of machine learning is the lack of consistent and reliable…

neural vocoders machine learning

Subscale WaveRNN

You have read Efficient Neural Audio Synthesis aka the WaveRNN paper and would like to know more about how the subscale system works and how it can be implemented? This…

searching googling github

Ways to find answers

You start working on a task, you find a library that does everything you need. You start using the library, and then you get an error. You look at the documentation of…