Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319309700> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4319309700 abstract "Foreign accent conversion is an important and challenging problem due to significant differences in the manner of articulation and the speech prosody of different regional speakers. In this paper, we propose a new method for the problem of foreign accent conversion that uses Phonetic Posteriorgrams (PPGs) and Log-scale Fundamental frequency (Log-F0) to address the mismatches of phonetic and prosody. Furthermore, we propose using concentrated attention to improve the alignment of input sequences and mel-spectrograms. The concentrated attention selects the top k highest score values in the attention matrix row by row. In this way, the attention weight of the content related to the current sequence will be the largest. Our approach first trains a PPG extractor using LibriSpeech Corpus, which uses an end-to-end hybrid CTC-attention model. Then, the modified Tacotron2 based on concentrated attention is trained to model the relationships between PPGs and mel-spectrograms. In our proposed framework, the input of Tacotron2 is the concatenation of PPG embedding and normalized Log-scale fundamental frequency (Log-F0). In the convert stage, WaveGlow is modeled to generate speech, which is a streaming structure. To better verify the effectiveness of our proposed method, we also add some objective evaluation methods. These include Mel spectral distance, Object_MOS score, speaker similarity, and similarity in the embedding space of the entire speech. Experiments shows that our proposed concentrated attention method delivers comparable or better results than the previous foreign accent conversion method in terms of voice naturalness, speaker similarity to the source speaker, and accent similarity to the target speaker." @default.
- W4319309700 created "2023-02-08" @default.
- W4319309700 creator A5027499854 @default.
- W4319309700 creator A5038694318 @default.
- W4319309700 creator A5074886830 @default.
- W4319309700 date "2022-11-01" @default.
- W4319309700 modified "2023-09-27" @default.
- W4319309700 title "Foreign Accent Conversion using Concentrated Attention" @default.
- W4319309700 cites W1494198834 @default.
- W4319309700 cites W1892640180 @default.
- W4319309700 cites W2017742648 @default.
- W4319309700 cites W2023728986 @default.
- W4319309700 cites W2124331435 @default.
- W4319309700 cites W2125047278 @default.
- W4319309700 cites W2576309025 @default.
- W4319309700 cites W2888954148 @default.
- W4319309700 cites W2890402938 @default.
- W4319309700 cites W2905661106 @default.
- W4319309700 cites W2936718374 @default.
- W4319309700 cites W2938583109 @default.
- W4319309700 cites W2955237921 @default.
- W4319309700 cites W2963252329 @default.
- W4319309700 cites W2963300588 @default.
- W4319309700 cites W2964243274 @default.
- W4319309700 cites W2972970915 @default.
- W4319309700 cites W2973142754 @default.
- W4319309700 cites W3015430779 @default.
- W4319309700 cites W3015719750 @default.
- W4319309700 cites W3083423753 @default.
- W4319309700 cites W3098557217 @default.
- W4319309700 cites W3135654121 @default.
- W4319309700 cites W3204009030 @default.
- W4319309700 doi "https://doi.org/10.1109/ickg55886.2022.00056" @default.
- W4319309700 hasPublicationYear "2022" @default.
- W4319309700 type Work @default.
- W4319309700 citedByCount "0" @default.
- W4319309700 crossrefType "proceedings-article" @default.
- W4319309700 hasAuthorship W4319309700A5027499854 @default.
- W4319309700 hasAuthorship W4319309700A5038694318 @default.
- W4319309700 hasAuthorship W4319309700A5074886830 @default.
- W4319309700 hasConcept C103278499 @default.
- W4319309700 hasConcept C115961682 @default.
- W4319309700 hasConcept C121332964 @default.
- W4319309700 hasConcept C134537474 @default.
- W4319309700 hasConcept C154945302 @default.
- W4319309700 hasConcept C2776756274 @default.
- W4319309700 hasConcept C28490314 @default.
- W4319309700 hasConcept C41008148 @default.
- W4319309700 hasConcept C45273575 @default.
- W4319309700 hasConcept C542774811 @default.
- W4319309700 hasConcept C62520636 @default.
- W4319309700 hasConceptScore W4319309700C103278499 @default.
- W4319309700 hasConceptScore W4319309700C115961682 @default.
- W4319309700 hasConceptScore W4319309700C121332964 @default.
- W4319309700 hasConceptScore W4319309700C134537474 @default.
- W4319309700 hasConceptScore W4319309700C154945302 @default.
- W4319309700 hasConceptScore W4319309700C2776756274 @default.
- W4319309700 hasConceptScore W4319309700C28490314 @default.
- W4319309700 hasConceptScore W4319309700C41008148 @default.
- W4319309700 hasConceptScore W4319309700C45273575 @default.
- W4319309700 hasConceptScore W4319309700C542774811 @default.
- W4319309700 hasConceptScore W4319309700C62520636 @default.
- W4319309700 hasLocation W43193097001 @default.
- W4319309700 hasOpenAccess W4319309700 @default.
- W4319309700 hasPrimaryLocation W43193097001 @default.
- W4319309700 hasRelatedWork W2090830255 @default.
- W4319309700 hasRelatedWork W2154644810 @default.
- W4319309700 hasRelatedWork W2928664166 @default.
- W4319309700 hasRelatedWork W3114453927 @default.
- W4319309700 hasRelatedWork W3160844600 @default.
- W4319309700 hasRelatedWork W3162491754 @default.
- W4319309700 hasRelatedWork W3213248030 @default.
- W4319309700 hasRelatedWork W4309043622 @default.
- W4319309700 hasRelatedWork W4319309700 @default.
- W4319309700 hasRelatedWork W4319862665 @default.
- W4319309700 isParatext "false" @default.
- W4319309700 isRetracted "false" @default.
- W4319309700 workType "article" @default.