29 citations · 84 across the 16 of their papers we have counts for
6 papers · 1 filter
Multimodal Contrastive Representation Learning Based Voice Conversion for Electrolaryngeal Speech Enhancement
Ding Ma, Jinyi Mi, Jiajun He +3
Electrolaryngeal (EL) speech suffers from severe acoustic mismatches with normal speech, resulting in degraded naturalness and intelligibility. These mismatches also make sequence-…
AAS-VC: On the Generalization Ability of Automatic Alignment Search based Non-autoregressive Sequence-to-sequence Voice Conversion
Wen-Chin Huang, Kazuhiro Kobayashi, Tomoki Toda
Non-autoregressive (non-AR) sequence-to-seqeunce (seq2seq) models for voice conversion (VC) is attractive in its ability to effectively model the temporal structure while enjoying…
Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders
Lester Phillip Violeta, Wen-Chin Huang, Ding Ma +3
We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have prov…
Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion
Ding Ma, Lester Phillip Violeta, Kazuhiro Kobayashi +1
Sequence-to-sequence (seq2seq) voice conversion (VC) models have greater potential in converting electrolaryngeal (EL) speech to normal speech (EL2SP) compared to conventional VC m…
A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
Wen-Chin Huang, Kazuhiro Kobayashi, Yu-Huai Peng +4
We propose a new paradigm for maintaining speaker identity in dysarthric voice conversion (DVC). The poor quality of dysarthric speech can be greatly improved by statistical VC, bu…
Non-autoregressive sequence-to-sequence voice conversion
Tomoki Hayashi, Wen-Chin Huang, Kazuhiro Kobayashi +1
This paper proposes a novel voice conversion (VC) method based on non-autoregressive sequence-to-sequence (NAR-S2S) models. Inspired by the great success of NAR-S2S models such as…