Zero-Shot Voice Conversion with Adjusted Speaker Embeddings and Simple Acoustic Features.
Zhiyuan TanJianguo WeiJunhai XuYuqing HeWenhuan LuPublished in: ICASSP (2021)
Keyphrases
- acoustic features
- speaker verification
- mel frequency cepstral coefficients
- automatic speech recognition
- speech signal
- dimensionality reduction
- speech recognition
- pattern recognition
- emotion recognition
- visual features
- human computer interaction
- cross correlation
- multi modal
- text classification
- music information retrieval
- feature vectors
- object recognition
- similarity measure
- music genre classification