LearningDe-identifiedRepresentationsofProsodyfromRawAudioJackWeston1RaphaëlLenain1UdeepaMeepegama1EmilFristed1AbstractThephoneticproblemhasautomaticspeechrecognition(ASR)asitsobvioususe-case.Inrec...
WaveFlow:ACompactFlow-basedModelforRawAudioWeiPing1KainanPeng1KexinZhao1ZhaoSong1Abstractgenerates1-Dwaveformsamplesatinference.Asaresult,WaveNetisprohibitivelyslowforspeechsynthesisandoneInthiswor...
FloWaveNet:AGenerativeFlowforRawAudioSungwonKim1Sang-gilLee1JongyoonSong1JaehyeonKim2SungrohYoon13Abstractetal.,2018;Ariketal.,2017b;a;Pingetal.,2017;Jiaetal.,2018).However,thepracticalapplicationo...
DiscoveringContextEffectsfromRawChoiceDataArjunSeshadri1AlexanderPeysakhovich2JohanUgander1AbstractThemostwellknownandwidelyusedRUMisthecondi-tionalmultinomiallogit(MNL),alsocalledtheLucemodel,Many...