speech-recognition   325

« earlier    

Home - Vocalize
"We have leveraged decades of experience from the field of Audiology and created a software suite designed to evaluate the hearing capabilities of AI powered virtual assistants such as Alexa, Siri, Cortana, Bixby and Google Assistant. We apply our protocols across spoken language variables such as volume level, background noise, distance and cadence. This creates a detailed description of the virtual assistant hearing ability."
speech-recognition  voxable  add-to-list 
29 days ago by techpeace
These companies are shrinking the voice recognition 'accent gap' | VentureBeat
y the end of 2018, the Google Assistant will support over 30 languages. Qualcomm has developed on-device models that can recognize words and phrases with 95 percent accuracy. And Microsoft’s call center solution is able to transcribe conversations more accurately than a team of humans.

[Speechmatic's] language pack — dubbed Global English — is the result of thousands of hours of speech data from over 40 countries and “tens of billions” of words. It supports “all major” English accents for speech-to-text transcription, and it’s built on the back of Speechmatic’s Automatic Linguist, an AI-powered framework that learns the linguistic foundations of new languages by drawing on patterns identified in known ones.

Nuance says it employs several methods to ensure its voice recognition models understand equally well speakers of the roughly 80 languages its products support
voice  accents  speech-recognition  speechmatics  nuance 
4 weeks ago by lavallee
SeanNaren/deepspeech.pytorch: Speech Recognition using DeepSpeech2.
GitHub is where people build software. More than 27 million people use GitHub to discover, fork, and contribute to over 80 million projects.
speech-recognition  pytorch  speech  audio  deep-learning 
may 2018 by nharbour
speech-recognition/app.js at master · syzer/speech-recognition
GitHub is where people build software. More than 27 million people use GitHub to discover, fork, and contribute to over 80 million projects.
bullshit  bingo  machine-learning  deep-learning  node.js  webkit  speech  speech-recognition 
may 2018 by nharbour

« earlier    

related tags

@-public  accents  acm  acoustic  adaptation  adapting  add-to-list  ai  alexa  algorithm  amazon-transcribe  api  apple-behind-the-scenes  apple  art  article  artificial-intelligence  asr  attacks  audio  auphonic  australia  baidu  best  bingo  bullshit  cmu  code  command  component  computer-vision  content-samurai  conversational  cortana  culture  dataset  datasets  deep-learning  develop  dictation  dictionary  discussion  domotics  dragon-dictate  emberjs  exploits  facebook  feature-engineering  feature-extraction  features  fft  gcp  google-cloud-speech  google-now  grapheme-to-phoneme  hacker-news-comments  health  human  ibm  image-recognition  insane  internet-of-things  ios  iot  irish-diaspora  jan18  javascript-bits  javascript  js  language-assessment  learning  libraries  library  linguistics  listening-table  mac  machine-learning  machine_learning  machinelearning  macos  mar17  markov-chain  microphone  microsoft  ml  model  models  mozilla  natural-language-processing  neural-network  neural  nlp  node.js  nov16  nuance  open-source  opensource  papers  pl__python  pmz  programming  pronunciation  python  pytorch  raspberry-pi  recognition  reference  research  review  rnn  rsi  sdk  security  separation  siri  software  spectrogram  speech-generation  speech-synthesis  speech-to-text  speech  speechmatics  speechrecognition  sphinx  svr  switchboard  teaching  technology  tensor-flow  tensorflow  text-to-speech  tips  tool  toolkit  tools  training  transcription  tutorial  user-interface  vision  voice-control  voice-interfaces  voice-recognition  voice  voxable  vue  watson  wavenet  wearable  web-speech-api  webkit  webmarketingfree  wikipedia  wit.ai  wtf 

Copy this bookmark: