e2e   466

« earlier    

Smashtest - A language for rapidly describing and deploying test cases
Greatly speed up your automated testing by writing tests in a tree-like format.

Trees represent how we think when we're testing. They allow us to list all the permutations that branch off from any given point.
e2e  javascript  library  testing 
2 hours ago by benjamincharity
[1906.03402] Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
Recent work has explored sequence-to-sequence latent variable models for expressive speech synthesis (supporting control and transfer of prosody and style), but has not presented a coherent framework for understanding the trade-offs between the competing methods. In this paper, we propose embedding capacity as a unified method of analyzing the behavior of latent variable models of speech, comparing existing heuristic (non-variational) methods to variational methods that are able to explicitly constrain capacity using an upper bound on representational mutual information. In our proposed model, we show that by adding conditional dependencies to the variational posterior such that it matches the form of the true posterior, the same model can be used for high-precision prosody transfer, text-agnostic style transfer, and generation of natural-sounding prior samples. For multi-speaker models, the proposed model is able to preserve target speaker identity during inter-speaker prosody transfer and when drawing samples from the latent prior. Lastly, we introduce a method for decomposing embedding capacity hierarchically across two sets of latents, allowing a portion of the latent variability to be specified and the remaining variability sampled from a learned prior.
speech-synthesis  neural-net  e2e 
22 days ago by arsyed
Cypress tips and tricks
"A few tips on getting the most out of E2E testing tool Cypress"
Cypress  test  e2e  tips  clevermarks 
27 days ago by nhoizey
A Plan to Stop Breaches With Dead Simple Database Encryption | WIRED
So the idea of field level E2E encryption for MongoDB gains legs, but I think the MongoDB security horse has already left the barn?
MongoDb  e2e  field  level  encryption  computer  science  research  technology 
4 weeks ago by asteroza
Automating Thankful Dinners in E2:E (mid game) without AE2 - Album on Imgur
Post with 23 views. Automating Thankful Dinners in E2:E (mid game) without AE2
mc  e2e  mc_build 
6 weeks ago by taotau
[1810.13107] End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator
The speech chain mechanism integrates automatic speech recognition (ASR) and text-to-speech synthesis (TTS) modules into a single cycle during training. In our previous work, we applied a speech chain mechanism as a semi-supervised learning. It provides the ability for ASR and TTS to assist each other when they receive unpaired data and let them infer the missing pair and optimize the model with reconstruction loss. If we only have speech without transcription, ASR generates the most likely transcription from the speech data, and then TTS uses the generated transcription to reconstruct the original speech features. However, in previous papers, we just limited our back-propagation to the closest module, which is the TTS part. One reason is that back-propagating the error through the ASR is challenging due to the output of the ASR are discrete tokens, creating non-differentiability between the TTS and ASR. In this paper, we address this problem and describe how to thoroughly train a speech chain end-to-end for reconstruction loss using a straight-through estimator (ST). Experimental results revealed that, with sampling from ST-Gumbel-Softmax, we were able to update ASR parameters and improve the ASR performances by 11\% relative CER reduction compared to the baseline.
asr  speech-synthesis  e2e  loss-functions  feedback-loss 
9 weeks ago by arsyed
[1811.01690] Cycle-consistency training for end-to-end speech recognition
This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR systems, it still requires a large amount of paired data, i.e., speech utterances and their transcriptions. Cycle-consistency losses have been recently proposed as a way to mitigate the problem of limited paired data. These approaches compose a reverse operation with a given transformation, e.g., text-to-speech (TTS) with ASR, to build a loss that only requires unsupervised data, speech in this example. Applying cycle consistency to ASR models is not trivial since fundamental information, such as speaker traits, are lost in the intermediate text bottleneck. To solve this problem, this work presents a loss that is based on the speech encoder state sequence instead of the raw speech signal. This is achieved by training a Text-To-Encoder model and defining a loss based on the encoder reconstruction error. Experimental results on the LibriSpeech corpus show that the proposed cycle-consistency training reduced the word error rate by 14.7% from an initial model trained with 100-hour paired data, using an additional 360 hours of audio data without transcriptions. We also investigate the use of text-only data mainly for language modeling to further improve the performance in the unpaired data training scenario.
asr  e2e  cycle-consistency  loss-functions 
9 weeks ago by arsyed
Sequence-level Knowledge Distillation for Model Compression of Attention-based Sequence-to-sequence Speech Recognition - IEEE Conference Publication
We investigate the feasibility of sequence-level knowledge distillation of Sequence-to-Sequence (Seq2Seq) models for Large Vocabulary Continuous Speech Recognition (LVCSR). We first use a pre-trained larger teacher model to generate multiple hypotheses per utterance with beam search. With the same input, we then train the student model using these hypotheses generated from the teacher as pseudo labels in place of the original ground truth labels. We evaluate our proposed method using Wall Street Journal (WSJ) corpus. It achieved up to 9.8× parameter reduction with accuracy loss of up to 7.0% word-error rate (WER) increase.
asr  knowledge-distillation  e2e 
12 weeks ago by arsyed

« earlier    

related tags

acceptance  acceptancetesting  acceptancetests  active-learning  activitypub  alexa  android  angular  api  app  apple  appshell  architecture  asr-error  asr  attention  audio  automation  aws  babel  bigquery  briar  browser  char2wav  chat  chrome  clarinet  clever  clevermarks  client  code  codebuild  collaboration  communication  community  computer  concept  concourse  convnet  copy  crypto  cryptography  css  ctc  cucumber  curve  cycle-consistency  cypress.io  cypress  cypressio  dashboard  deep-learning  deployment  design  development  devops  dialogue  docker  e2etesting  ebay  education  eliptic  elixir  encrypted  encryption  end-to-end  end2end  endtoend  espnet  facebook  featureflags  feedback-loss  field  file  fileshare  framework  france  frontend  gdpr  ghostinspector  golang  graphql  handlebars  headless  html  im  imessage  instant  integration  integrationtesting  interaction  interesting_companies  internet  ios  iot  iphone  jabber  javascript  js  jsx  k8s  kaldi  keybase  knowledge-distillation  kubernetes  label:try_out  level  library  libs  list  lit-html  litepub  loss-functions  low-resource  m2m  mailing  matrix  mc  mc_build  message  messaging  messenger  metamask  microservices  mocha  mongodb  mqtt  multilingual  music-transcription  music  network  networking  neural-net  nightwatchjs  nlu  node  note  notepad  notifications  omemo  open-source  openpgp  openshift  opensource  owasp  phoenix  politics  post-quantum  pqe  pre-training  privacy  production  programming  protocol  protractor  puppeteer  pwa  pytorch  react-native  react.js  react  regression  representation-learning  research  riot  rnn  science  screenshot  sdlc  secure  security  seq2seq  sequential-modeling  server  service  serviceworker  sharing  signal  slack  slide  slu  software  specification  speech-synthesis  speech  standard  style-transfer  sync  tdd  techniques  technology  test  testing  tests  tips  todo  tool  transfer-learning  tutorial  type:application  typescript  ui  unittesting  upload  vad  video  videos  visual-testing  vuejs  wave  web_design  webbrowser  whatsapp  wix  workshops  xhr  xmpp  zap 

Copy this bookmark:



description:


tags: