Matches in SemOpenAlex for { <https://semopenalex.org/work/W3162305767> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3162305767 endingPage "41" @default.
- W3162305767 startingPage "28" @default.
- W3162305767 abstract "Traditionally, learning speech synthesis and speech recognition were investigated as two separate tasks. This separation hinders incremental development for concurrent synthesis and recognition, where partially-learned synthesis and partially-learned recognition must help each other throughout lifelong learning. This work is a paradigm shift—we treat synthesis and recognition as two intertwined aspects of a lifelong learning agent. Furthermore, in contrast to existing recognition or synthesis systems, babies do not need their mothers to directly supervise their vocal tracts at every moment during the learning. We argue that self-generated non-symbolic states/actions at fine-grained time level help such a learner as necessary temporal contexts. Here, we approach a new and challenging problem—how to enable an autonomous learning system to develop an artificial speaking motor for generating temporally-dense (e.g., frame-wise) actions on the fly without human handcrafting a set of symbolic states. The self-generated states/actions are Muscles-like, High-dimensional, Temporally-dense and Globally-smooth (MHTG), so that these states/actions are directly attended for concurrent synthesis and recognition for each time frame. Human teachers are relieved from supervising learner’s motor ends. The Candid Covariance-free Incremental (CCI) Principal Component Analysis (PCA) is applied to develop such an artificial speaking motor where PCA features drive the motor. Since each life must develop normally, each Developmental Network-2 (DN-2) reaches the same network (maximum likelihood, ML) regardless of randomly initialized weights, where ML is not just for a function approximator but rather an emergent Turing Machine. The machine-synthesized sounds are evaluated by both the neural network and humans with recognition experiments. Our experimental results showed learning-to-synthesize and learning-to-recognize-through-synthesis for phonemes. This work corresponds to a key step toward our goal to close a great gap toward fully autonomous machine learning directly from the physical world." @default.
- W3162305767 created "2021-05-24" @default.
- W3162305767 creator A5023171713 @default.
- W3162305767 creator A5074920063 @default.
- W3162305767 date "2021-11-01" @default.
- W3162305767 modified "2023-10-17" @default.
- W3162305767 title "Learning to recognize while learning to speak: Self-supervision and developing a speaking motor" @default.
- W3162305767 cites W1562462135 @default.
- W3162305767 cites W1821176968 @default.
- W3162305767 cites W1970209023 @default.
- W3162305767 cites W1997798784 @default.
- W3162305767 cites W2005313060 @default.
- W3162305767 cites W2011589116 @default.
- W3162305767 cites W2014022174 @default.
- W3162305767 cites W2025768430 @default.
- W3162305767 cites W2049765399 @default.
- W3162305767 cites W2064675550 @default.
- W3162305767 cites W2121122425 @default.
- W3162305767 cites W2131774270 @default.
- W3162305767 cites W2141681031 @default.
- W3162305767 cites W2141794189 @default.
- W3162305767 cites W2153633111 @default.
- W3162305767 cites W2165626265 @default.
- W3162305767 cites W2171928131 @default.
- W3162305767 cites W2332273449 @default.
- W3162305767 cites W2480770133 @default.
- W3162305767 cites W2506994639 @default.
- W3162305767 cites W2736334449 @default.
- W3162305767 cites W2760048934 @default.
- W3162305767 cites W2804740725 @default.
- W3162305767 cites W2889413431 @default.
- W3162305767 cites W2903561482 @default.
- W3162305767 cites W2910022993 @default.
- W3162305767 cites W2964002616 @default.
- W3162305767 cites W2966661 @default.
- W3162305767 cites W2973843421 @default.
- W3162305767 cites W3003523273 @default.
- W3162305767 cites W3089392285 @default.
- W3162305767 doi "https://doi.org/10.1016/j.neunet.2021.05.006" @default.
- W3162305767 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34082380" @default.
- W3162305767 hasPublicationYear "2021" @default.
- W3162305767 type Work @default.
- W3162305767 sameAs 3162305767 @default.
- W3162305767 citedByCount "2" @default.
- W3162305767 countsByYear W31623057672023 @default.
- W3162305767 crossrefType "journal-article" @default.
- W3162305767 hasAuthorship W3162305767A5023171713 @default.
- W3162305767 hasAuthorship W3162305767A5074920063 @default.
- W3162305767 hasConcept C107690735 @default.
- W3162305767 hasConcept C108771440 @default.
- W3162305767 hasConcept C119857082 @default.
- W3162305767 hasConcept C126042441 @default.
- W3162305767 hasConcept C154945302 @default.
- W3162305767 hasConcept C15744967 @default.
- W3162305767 hasConcept C169760540 @default.
- W3162305767 hasConcept C177264268 @default.
- W3162305767 hasConcept C19417346 @default.
- W3162305767 hasConcept C199360897 @default.
- W3162305767 hasConcept C28490314 @default.
- W3162305767 hasConcept C41008148 @default.
- W3162305767 hasConcept C50644808 @default.
- W3162305767 hasConcept C76155785 @default.
- W3162305767 hasConcept C97541855 @default.
- W3162305767 hasConceptScore W3162305767C107690735 @default.
- W3162305767 hasConceptScore W3162305767C108771440 @default.
- W3162305767 hasConceptScore W3162305767C119857082 @default.
- W3162305767 hasConceptScore W3162305767C126042441 @default.
- W3162305767 hasConceptScore W3162305767C154945302 @default.
- W3162305767 hasConceptScore W3162305767C15744967 @default.
- W3162305767 hasConceptScore W3162305767C169760540 @default.
- W3162305767 hasConceptScore W3162305767C177264268 @default.
- W3162305767 hasConceptScore W3162305767C19417346 @default.
- W3162305767 hasConceptScore W3162305767C199360897 @default.
- W3162305767 hasConceptScore W3162305767C28490314 @default.
- W3162305767 hasConceptScore W3162305767C41008148 @default.
- W3162305767 hasConceptScore W3162305767C50644808 @default.
- W3162305767 hasConceptScore W3162305767C76155785 @default.
- W3162305767 hasConceptScore W3162305767C97541855 @default.
- W3162305767 hasLocation W31623057671 @default.
- W3162305767 hasOpenAccess W3162305767 @default.
- W3162305767 hasPrimaryLocation W31623057671 @default.
- W3162305767 hasRelatedWork W1562959674 @default.
- W3162305767 hasRelatedWork W2919850041 @default.
- W3162305767 hasRelatedWork W2923653485 @default.
- W3162305767 hasRelatedWork W2957776456 @default.
- W3162305767 hasRelatedWork W3022038857 @default.
- W3162305767 hasRelatedWork W3036236109 @default.
- W3162305767 hasRelatedWork W4287755224 @default.
- W3162305767 hasRelatedWork W4319083788 @default.
- W3162305767 hasRelatedWork W4361026739 @default.
- W3162305767 hasRelatedWork W1629725936 @default.
- W3162305767 hasVolume "143" @default.
- W3162305767 isParatext "false" @default.
- W3162305767 isRetracted "false" @default.
- W3162305767 magId "3162305767" @default.
- W3162305767 workType "article" @default.