Meta's MMS is een project dat indrukwekkende vooruitgang heeft geboekt op het gebied van spraakherkenning en spraakproductie in meer dan 1.100 talen. Het maakt gebruik van bijbelvertalingen als dataset om spraak in verschillende talen te leren herkennen en genereren. Dit baanbrekende project draagt bij aan het doorbreken van taalbarrières en het bevorderen van taaldiversiteit.
De video bespreekt de nieuwste marketingstrategieën en hoe ze van toepassing zijn op de huidige markt. Het benadrukt het belang van social media en influencer marketing. Ook wordt de impact van gepersonaliseerde content op de consumentenervaring besproken.
hi guys and welcome to the voice of AI
my name is Chris Plante and some super
cool big big news from yesterday meta
have shared new progress on their AI
speech work the massively multilingual
speech project has now scaled speech to
text and text-to-speech to support over
1 100 languages which is a 10 times
increase from previous work MMS is a
game changer for the world of speech
recognition and speech generation
technology this project led by meta aims
to break down language barriers by
enabling machines to recognize and
produce speech in over 1 000 languages
covering 10 times more languages than
any existing speech recognition or
speech generation model with this
multi-model system people from all over
the world can access information and
communicate effectively in their
preferred language preserving linguistic
diversity across the globe one of the
biggest challenges in creating a
multi-modal system for speech
recognition and speech generation is
finding the vast amounts of label data
necessary for training such models
for most languages such data simply
doesn't exist making it almost
impossible to develop good quality
models for speech tasks however the MMS
project overcomes these challenges by
using the New Testament translations
which have audio recordings of people
reading the text in different languages
to create data sets of readings in an
over 1 100 languages this combined with
unlabeled audio recordings from various
Christian religious readings provides
label data for 1100 languages and
unlabeled data for nearly 4 000
languages the results of this project
shows that MMS models outperform
existing models and cover 10 times as
many languages their models also perform
equally well for male and female voices
let's have a quick look at the data okay
so the first graph shows character error
rates this is an analysis of potential
gender bias automatic speech recognition
models trained on MMS data have a SIM
error rate for male and female speakers
based on the fleur's benchmark and now
here on character error raids meta
trained multilingual speech recognition
models on over 1 100 languages as the
number of languages increases
performance does decrease but only
slightly moving from 61 to 1107
languages increases the character error
rate by only about 0.4 but it increases
the language coverage by over 18 times
if we look here in the word error rate
you can see in a light for like
comparison with open ai's whisper meta
found that models trained on MMS data
achieve half the word error rate but MMS
covers 11 times more languages this
demonstrates that their model can
perform very well compared to the best
current speech models and finally the
error rates in percentage meta trained a
language identification model for over 4
000 languages using their data sets as
well as existing data sets such as flurs
and common voice and evaluated it on the
fleurs language identification task it
turns out that supporting 40 times the
number of languages still results in a
very good performance furthermore the
MMS project provides code and models
publicly so that other researchers can
build upon their work and make
contributions to preserve the language
diversity in the world while the models
aren't perfect and run the risk of
mistranslating Select words or phrases
the project recognizes the importance of
collaboration within the AI Community to
ensure that AI Technologies are
developed responsibly this project has
the power to make significant impact on
the future of communication breaking
down the language barriers that have
historically existed and encouraging
people to preserve their languages the
vision is to create a world where
technology can understand and
communicate in any language effectively
preserving linguistic diversity while
this is really the beginning the
massively multilingual speech MMS
project represents a significant step
towards achieving this goal with the
advancement of Technology the future is
looking bright for communication across
languages and cultures
thanks for watching the video today
please don't forget to like And
subscribe and join me on the journey to
unlock the potential of AI
if you have any questions or any
feedback please leave them in the
comments section below I'll be happy to
read them so I'll see you next time and
all the very best I'm Chris from the
voice of AI cheers and bye-bye now
foreign
Meta, formerly known as Facebook, has unveiled its progress on a new project called "Massively Multilingual Speech" (MMS), which has scaled speech-to-text and text-to-speech support for over 1,100 languages. This is a 10 times increase from the company's previous speech recognition work.
MMS is focused on breaking down language barriers by enabling machines to recognize and produce speech in over 1,000 languages, which is an extraordinary breakthrough. By using the New Testament translations, which have recorded audio of people reading the text in different languages, MMS creates a dataset of readings in over 1,100 languages. This, combined with unlabeled audio recordings from various Christian religious readings, provides label data for 1,100 languages and unlabeled data for nearly 4,000 languages.
MMS's ability to recognize and produce speech in multiple languages has the potential to significantly impact customer support across industries. With more languages recognized, customer support becomes more easily accessible to people worldwide, preserving linguistic diversity across the globe. However, it's important to note that these models aren't perfect and may mistranslate certain words or phrases. Collaboration within the AI Community is necessary to ensure that AI Technologies are developed responsibly and preserve language diversity in the world.
MMS models outperform existing speech models and cover 10 times as many languages. Furthermore, the MMS project provides code and models publicly, allowing other researchers to build upon their work and contribute to preserving language diversity. With the advancement of technology, the future is looking bright for communication across languages and cultures.
Klantenondersteuningstaal – 7 uitdrukkingen om niet te gebruiken in de klantenondersteuning
Vermijd 7 negatieve uitdrukkingen in klantenondersteuning om de klantervaring te verbeteren. Investeer in training en ontwikkeling van medewerkers. Maak een GRATIS account aan.
LiveAgent is een klantenservicesoftware die klachtenbeheerssysteem, cliëntenportaalsoftware en e-mailbeheersoftware biedt. Het heeft ook integraties, alternatieven en functies. Er is een ondersteuningsportaal en gegevensmigratie beschikbaar, en het bedrijf biedt ook een demo, prijzen en aanvragen voor offertes. LiveAgent heeft verschillende prijzen en biedt voornamelijk klantenservicesoftware, VoIP-telefoonsystemen, selfservicesoftware en inkomend callcentersoftware. Het bedrijf heeft ook een blog, woordenlijst, sjablonen en webinars. LiveAgent biedt ook een typetest en een kostencalculator. Het bedrijf heeft sales contacten en biedt een partnerprogramma, nieuwsbrief en demo. Het installatieproces wordt door het bedrijf goed begeleid.
Stressvrije software voor ondersteuning van sociale media
LiveAgent is een goede tool voor het beheer van sociale media, waarmee bedrijven hun klantenbetrokkenheid en klantenbehoud kunnen verbeteren. Door uitzonderlijke klantenservice te bieden, kunnen bedrijven tevreden klanten behouden en hun klantentevredenheid verhogen. Meer dan 30.000 bedrijven zijn al overtuigd van LiveAgent en hebben succesverhalen en getuigenissen gedeeld. LiveAgent past zich aan aan de bedrijfsgrootte en sector en heeft organisaties van alle typen en groottes geholpen, inclusief start-ups, ondernemingen, overheid, onderwijs en NGO's in verschillende industrieën.
Join our community of happy clients and provide excellent customer support with LiveAgent.
Onze website maakt gebruik van cookies. Door verder te gaan, gaan we ervan uit dat we uw toestemming hebben om cookies te plaatsen zoals beschreven in onze privacy- en cookiebeleid.