Questions tagged [voice]
The voice tag has no usage guidance.
6
questions
0
votes
1
answer
216
views
How to create AI voice generator for fantasy language?
I have a "fantasy language" (a conlang), which has a very simple pronunciation system. Every letter represents one sound, as opposed to English, where you can have the same sound with ...
- 263
0
votes
0
answers
723
views
How can I force tortoise-tts to use the same voice throughout a generate speech file?
From time to time, a sentence or a fragment of a sentence somewhere in the text will be read with a different voice.
Example with this text.txt:
What makes jee pee tee-3+ so advanced and powerful? ...
- 5,650
1
vote
0
answers
95
views
How can I get tortoise-tts to pronounce acronyms correctly?
I'm trying to get tortoise-tts to pronounce acronyms correctly. Example of text that I'd like tortoise-tts to generate an audio file for: ...
- 5,650
0
votes
1
answer
39
views
What is the difference between VAD and Speaker Segmentation?
I'm not sure I can distinguish and understand the difference between:
VAD (Voice Activity Detection) and
Speaker Segmentation
...
- 363
0
votes
0
answers
33
views
Why speaker diarization DER on Ego4D dataset is so bad?
According to: https://huggingface.co/pyannote/speaker-diarization,
the performacne of PyAnnote speaker diarization on Ego4D ...
- 363
0
votes
0
answers
21
views
How the embedding model (x-vectors) trained?
I read this paper: X-Vectors: Robust DNN Embeddings for Speaker Recognition which describes how PyAnnote embedding block works.
I'm not sure I understand how the X-Vector model was trained and tested:
...
- 363