Paper Info
Title
Mandarin Electrolaryngeal Speech Voice Conversion with Sequence-to-Sequence Modeling
Abstract
The electrolaryngeal speech (EL speech) is typically spoken with an electrolarynx device that generates excitation signals to substitute human vocal fold vibrations. Because the excitation signals cannot perfectly characterize sound sources generated by vocal folds, the naturalness and intelligibility of the EL speech are inevitably worse than that of the natural speech (NL speech). To improve speech naturalness, statistical models, such as Gaussian mixture models and deep-learning-based models, have been employed for EL speech voice conversion (ELVC). The ELVC task aims to convert EL speech into NL speech through an ELVC model. To implement a frame-wise ELVC system, accurate feature alignment is crucial for model training. However, the abnormal acoustic characteristics of the EL speech cause misalignments and accordingly limit the ELVC performance. To address this issue, we propose a novel ELVC system based on sequence-to-sequence (seq2seq) modeling with text-to-speech (TTS) pretraining. The seq2seq model involves an attention mechanism to concurrently perform representation learning and alignment. Meanwhile, TTS pretraining provides efficient training with limited data. Experimental results show that the proposed ELVC system yields notable improvements in terms of standardized evaluation metrics and subjective listening tests over a well-known frame-wise ELVC system.
Year
DOI
Venue
2021
10.1109/ASRU51503.2021.9687908
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
Keywords
DocType
ISBN
electrolaryngeal speech,voice conversion,sequence-to-sequence learning,transformer,pretraining
Conference
978-1-6654-3740-0
Citations 
PageRank 
References 
0
0.34
0
Authors
9
Name
Order
Citations
PageRank
Ming-Chi Yen100.34
Wen-Chin Huang200.34
Kazuhiro Kobayashi300.34
Yu-Huai Peng484.23
Shu-Wei Tsai500.34
Yu Tsao600.68
Tomoki Toda71874167.18
Jyh-Shing Roger Jang852556.34
Hsin-Min Wang901.35