Torch, TF, Lasagne code for audio style transfer.

http://dmitryulyanov.github.io/audio-texture-synthesis-and-style-transfer/

#dl #audio #styletransfer #torch #tf #lasagne

Google has set up a new milestone for speech generation: "Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model"

You can listen to generated samples at: https://google.github.io/tacotron/

Paper: https://arxiv.org/abs/1703.10135

#audio #arxiv #google #breakthrough #generative

Google published new article about voice cloning: Expressive Speech Synthesis with Tacotron

link: https://research.googleblog.com/2018/03/expressive-speech-synthesis-with.html
samples: https://google.github.io/tacotron/publications/global_style_tokens/

#wavenet #audio #speech #deeplearning

New model to naturally detect depression in conversations

Link: http://news.mit.edu/2018/neural-network-model-detect-depression-conversations-0830

#nlp #audio #dl

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model

High-quality #speechrecognition systems require large amounts of data—yet many languages have little data available. Check out new research into an end-to-end system trained as a single model allowing for real-time multilingual speech recognition.

Link: https://ai.googleblog.com/2019/09/large-scale-multilingual-speech.html

#speech #audio #DL #Google

​​Online speech recognition with wav2letter@anywhere

Facebook have open-sourced wav2letter@anywhere, an inference framework for online speech recognition that delivers state-of-the-art performance.

Link: https://ai.facebook.com/blog/online-speech-recognition-with-wav2letteranywhere/

#wav2letter #audiolearning #soundlearning #sound #acoustic #audio #facebook

​​MMS: Scaling Speech Technology to 1000+ languages

Get ready for a breakthrough in speech technology that is set to revolutionize the world of communication! The field, which has so far been restricted to around a hundred languages, barely scratches the surface of the more than 7,000 languages spoken globally. The Massively Multilingual Speech (MMS) project is taking a monumental leap to bridge this gap, increasing the number of supported languages by an astounding 10 to 40 times, depending on the task. This unprecedented expansion will be a game-changer, significantly improving global access to information and creating a more inclusive digital landscape.

This incredible feat is achieved through the creation of a new dataset drawn from publicly available religious texts and the strategic implementation of self-supervised learning. The MMS project's achievements are staggering, including the development of pre-trained wav2vec 2.0 models for 1,406 languages, a single multilingual automatic speech recognition model for 1,107 languages, speech synthesis models for as many languages, and a language identification model for a whopping 4,017 languages. Even more impressive is the significant improvement in accuracy - our multilingual speech recognition model more than halves the word error rate of Whisper on 54 languages of the FLEURS benchmark, despite being trained on a significantly smaller dataset.

Paper link: https://research.facebook.com/publications/scaling-speech-technology-to-1000-languages/
Blogpost link: https://ai.facebook.com/blog/multilingual-model-speech-recognition/
Code link: https://github.com/facebookresearch/fairseq/tree/main/examples/mms

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-mms
#deeplearning #speechrecognition #tts #audio