Сөйлеушіні енгізу
method
ID: speakerembedding
Related Papers
Incorporating speaker embedding and post-filter network for improving speaker similarity of personalized speech synthesis system
AbstractIn recent years, speech synthesis system can generate speech with high speech quality. However, multi-speaker text-to-speech (TTS) system still require large amount of speech data for each target speaker. In …...
Evaluating the Effects of Embedding with Speaker Identity Information in Dialogue Summarization
AbstractAutomatic dialogue summarization is a task used to succinctly summarize a dialogue transcript while correctly linking the speakers and their speech, which distinguishes this task from a conventional document summarization. …...