Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049206033> ?p ?o ?g. }
- W3049206033 abstract "Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level representations based on WaveNet auto-encoders. Of particular interest in the ZeroSpeech Challenge 2019 were models with discrete latent variable such as the Vector Quantized Variational Auto-Encoder (VQVAE). However these models generate speech with relatively poor quality. In this work we aim to address this with two approaches: first WaveNet is used as the decoder and to generate waveform data directly from the latent representation; second, the low complexity of latent representations is improved with two alternative disentanglement learning methods, namely instance normalization and sliced vector quantization. The method was developed and tested in the context of the recent ZeroSpeech challenge 2020. The system output submitted to the challenge obtained the top position for naturalness (Mean Opinion Score 4.06), top position for intelligibility (Character Error Rate 0.15), and third position for the quality of the representation (ABX test score 12.5). These and further analysis in this paper illustrates that quality of the converted speech and the acoustic units representation can be well balanced." @default.
- W3049206033 created "2020-08-21" @default.
- W3049206033 creator A5011654282 @default.
- W3049206033 creator A5030528300 @default.
- W3049206033 date "2020-08-16" @default.
- W3049206033 modified "2023-09-24" @default.
- W3049206033 title "Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders" @default.
- W3049206033 cites W1522301498 @default.
- W3049206033 cites W1665214252 @default.
- W3049206033 cites W2005708641 @default.
- W3049206033 cites W2128032727 @default.
- W3049206033 cites W2242818861 @default.
- W3049206033 cites W2346964103 @default.
- W3049206033 cites W2395899413 @default.
- W3049206033 cites W2402146185 @default.
- W3049206033 cites W2502312327 @default.
- W3049206033 cites W2514741789 @default.
- W3049206033 cites W2519091744 @default.
- W3049206033 cites W2547039119 @default.
- W3049206033 cites W2598638573 @default.
- W3049206033 cites W2603777577 @default.
- W3049206033 cites W2785860501 @default.
- W3049206033 cites W2786608204 @default.
- W3049206033 cites W2786902352 @default.
- W3049206033 cites W2787447541 @default.
- W3049206033 cites W2789543585 @default.
- W3049206033 cites W2792995953 @default.
- W3049206033 cites W2808697642 @default.
- W3049206033 cites W2940544976 @default.
- W3049206033 cites W2950414763 @default.
- W3049206033 cites W2951004968 @default.
- W3049206033 cites W2963609956 @default.
- W3049206033 cites W2963618559 @default.
- W3049206033 cites W2963799213 @default.
- W3049206033 cites W2963830550 @default.
- W3049206033 cites W2964243274 @default.
- W3049206033 cites W2970971581 @default.
- W3049206033 cites W2972374322 @default.
- W3049206033 cites W2972659941 @default.
- W3049206033 cites W2972841524 @default.
- W3049206033 cites W2972867623 @default.
- W3049206033 cites W2972943112 @default.
- W3049206033 cites W2996383576 @default.
- W3049206033 cites W3095361818 @default.
- W3049206033 cites W3125709657 @default.
- W3049206033 doi "https://doi.org/10.48550/arxiv.2008.06892" @default.
- W3049206033 hasPublicationYear "2020" @default.
- W3049206033 type Work @default.
- W3049206033 sameAs 3049206033 @default.
- W3049206033 citedByCount "2" @default.
- W3049206033 countsByYear W30492060332021 @default.
- W3049206033 crossrefType "posted-content" @default.
- W3049206033 hasAuthorship W3049206033A5011654282 @default.
- W3049206033 hasAuthorship W3049206033A5030528300 @default.
- W3049206033 hasBestOaLocation W30492060331 @default.
- W3049206033 hasConcept C101738243 @default.
- W3049206033 hasConcept C108583219 @default.
- W3049206033 hasConcept C111472728 @default.
- W3049206033 hasConcept C111919701 @default.
- W3049206033 hasConcept C118505674 @default.
- W3049206033 hasConcept C121332964 @default.
- W3049206033 hasConcept C134537474 @default.
- W3049206033 hasConcept C136886441 @default.
- W3049206033 hasConcept C138885662 @default.
- W3049206033 hasConcept C144024400 @default.
- W3049206033 hasConcept C153180895 @default.
- W3049206033 hasConcept C154945302 @default.
- W3049206033 hasConcept C19165224 @default.
- W3049206033 hasConcept C199833920 @default.
- W3049206033 hasConcept C28490314 @default.
- W3049206033 hasConcept C41008148 @default.
- W3049206033 hasConcept C51167844 @default.
- W3049206033 hasConcept C60048801 @default.
- W3049206033 hasConcept C62520636 @default.
- W3049206033 hasConceptScore W3049206033C101738243 @default.
- W3049206033 hasConceptScore W3049206033C108583219 @default.
- W3049206033 hasConceptScore W3049206033C111472728 @default.
- W3049206033 hasConceptScore W3049206033C111919701 @default.
- W3049206033 hasConceptScore W3049206033C118505674 @default.
- W3049206033 hasConceptScore W3049206033C121332964 @default.
- W3049206033 hasConceptScore W3049206033C134537474 @default.
- W3049206033 hasConceptScore W3049206033C136886441 @default.
- W3049206033 hasConceptScore W3049206033C138885662 @default.
- W3049206033 hasConceptScore W3049206033C144024400 @default.
- W3049206033 hasConceptScore W3049206033C153180895 @default.
- W3049206033 hasConceptScore W3049206033C154945302 @default.
- W3049206033 hasConceptScore W3049206033C19165224 @default.
- W3049206033 hasConceptScore W3049206033C199833920 @default.
- W3049206033 hasConceptScore W3049206033C28490314 @default.
- W3049206033 hasConceptScore W3049206033C41008148 @default.
- W3049206033 hasConceptScore W3049206033C51167844 @default.
- W3049206033 hasConceptScore W3049206033C60048801 @default.
- W3049206033 hasConceptScore W3049206033C62520636 @default.
- W3049206033 hasLocation W30492060331 @default.
- W3049206033 hasLocation W30492060332 @default.
- W3049206033 hasOpenAccess W3049206033 @default.
- W3049206033 hasPrimaryLocation W30492060331 @default.
- W3049206033 hasRelatedWork W2769034141 @default.
- W3049206033 hasRelatedWork W3049206033 @default.
- W3049206033 hasRelatedWork W3090528452 @default.