Groups Similar Look up By Text Browse About



Similar articles
Article Id Title Prob Score Similar Compare
135315 VENTUREBEAT 2019-5-15:
Google’s Translatotron is an end-to-end model that mimics human voices
1.000 Find similar Compare side-by-side
135401 ENGADGET 2019-5-15:
Google's Translatotron can translate speech in the speaker's voice
0.974 0.636 Find similar Compare side-by-side
135583 THENEXTWEB 2019-5-16:
Google’s new AI can help you speak another language in your own voice
0.888 0.598 Find similar Compare side-by-side
135714 THEVERGE 2019-5-17:
Google’s prototype AI translator translates your tone as well as your words
0.324 0.564 Find similar Compare side-by-side
135374 TECHCRUNCH 2019-5-15:
Google’s Translatotron converts one spoken language to another, no text involved
0.941 0.529 Find similar Compare side-by-side
135495 VENTUREBEAT 2019-5-16:
Microsoft makes Google’s BERT NLP model better
0.054 0.513 Find similar Compare side-by-side
135067 VENTUREBEAT 2019-5-13:
Amazon Alexa scientists retrain an English-language AI model on Japanese
0.015 0.488 Find similar Compare side-by-side
135607 VENTUREBEAT 2019-5-16:
Alexa speech normalization AI reduces errors by up to 81%
0.439 Find similar Compare side-by-side
135235 VENTUREBEAT 2019-5-14:
IBM’s AI performs state-of-the-art broadcast news captioning
0.436 Find similar Compare side-by-side
135633 VENTUREBEAT 2019-5-16:
Google’s Live Transcribe is getting sound events and transcription saving
0.364 Find similar Compare side-by-side
135316 ARSTECHNICA 2019-5-15:
No, someone hasn’t cracked the code of the mysterious Voynich manuscript
0.352 Find similar Compare side-by-side
134990 TECHREPUBLIC 2019-5-13:
JavaScript and machine learning: Google shows what's possible using the web programming language
0.345 Find similar Compare side-by-side
135193 TECHREPUBLIC 2019-5-14:
Beginner's guide for TensorFlow: The basics of Google's machine-learning library
0.331 Find similar Compare side-by-side
135363 THEVERGE 2019-5-15:
AI translation boosted eBay sales more than 10 percent
0.322 Find similar Compare side-by-side
135192 VENTUREBEAT 2019-5-14:
Google Assistant launches on Sonos speakers
0.307 Find similar Compare side-by-side
135342 TECHREPUBLIC 2019-5-15:
10 reasons to consider switching your company's phone service to Google Voice
0.306 Find similar Compare side-by-side
135108 VENTUREBEAT 2019-5-14:
Transform 2019: Hear from the movers and shakers in AI
0.303 Find similar Compare side-by-side
135147 THEVERGE 2019-5-14:
Google Assistant is coming to the Sonos One and Beam today
0.302 Find similar Compare side-by-side
135002 THEVERGE 2019-5-13:
Use this cutting-edge AI text generator to write stories, poems, news articles, and more
0.298 Find similar Compare side-by-side
135532 VENTUREBEAT 2019-5-16:
Xnor launches embedded AI platform AI2Go
0.296 Find similar Compare side-by-side
135596 ENGADGET 2019-5-16:
Google's how-to videos explain Assistant's accessibility features
0.283 Find similar Compare side-by-side
135723 VENTUREBEAT 2019-5-17:
AI predicts PUBG player placement from stats and rankings
0.281 Find similar Compare side-by-side
135038 THEVERGE 2019-5-13:
How to stop Google from keeping your voice recordings
0.277 Find similar Compare side-by-side
135618 THEVERGE 2019-5-16:
Android’s Live Transcribe will let you save transcriptions and show ‘sound events’
0.269 Find similar Compare side-by-side
135265 TECHCRUNCH 2019-5-14:
Sonos finally gets Google Assistant integration
0.268 Find similar Compare side-by-side

1

ID: 135315

URL: https://venturebeat.com/2019/05/15/googles-translatotron-is-an-end-to-end-model-that-mimics-human-voices/

Date: 2019-05-15

Google’s Translatotron is an end-to-end model that mimics human voices

Google AI today shared details about Translatotron, an experimental AI system capable of direct translations of a persons voice into another language, an approach that allows synthesized translation of a persons voice to keep the sound of the original speakers voice. Traditionally, speech translation uses automatic speech recognition to convert speech to text, applies machine translation, then uses text-to-speech to produce a translation, but Translatotron is an end-to-end translation model. Translatotron can complete translations faster and with fewer complications than traditional cascaded models, researchers said. To the best of our knowledge, Translatotron is the first end-to-end model that can directly translate speech from one language into speech in another language. It is also able to retain the source speakers voice in the translated speech, a blog post on the subject reads. The BLEU score to measure machine translation quality found the experimental Translatotron to be lower quality than conventional cascade systems, but Translatotron achieved more accurate translations than baseline cascade translations. The emergence of end-to-end models for machine translation began with a paper by French researchers accepted at NeurIPS in 2016. To make Translatotron capable of carrying out end-to-end translations, researchers used a sequence-to-sequence model and spectrograms as input training data. A speaker encoder network is used to capture the character of the speakers voice, and multitask learning is used to predict words used by source and target speakers. Translatotron is spelled out in more detail in a paper published today titled Direct speech-to-speech translation with a sequence-to-sequence model. The release of Translatotron emerges a month after Google introduced SpecAugment, an AI model that uses computer vision and a variety of techniques to understand words from spectogram imagery. Translatotron could be applied for things like Google Assistants Interpreter Mode, which made its debut for Home speakers in January. Interpreter Mode is capable of listening and providing speech-to-speech translation in 27 languages. Companies like Google and Microsoft are also using their language translation chops as a way to win over iOS users. Translatotron is the latest advance in machine translation and language processing from Google. Last week at Googles I/O developer conference, Google shared that it shrunk its recurrent neural networks and language understanding models for on-device machine learning with smartphones, making Google Assistant up to 10 times faster. Google also introduced translations with Lens so your camera can translate more than 100 languages.