-
# Pronunciation scoring for non-native English
This task is to perform a pronunciation scoring of non-native speakers of English. Pronunciaiton scoring is important in computer-assisted language le…
-
Hi,
I am using this template and am benefiting from it a lot. Thank you very much for preparing it.
I tried to make subsections like the following, but the last subsection does not render:
## R…
-
Hi, I read your article entitled "rhythm of the rhythm" which is really great. I am currently working with low frequency spectrum characteristics to predict pathological speech intelligibility and it …
-
The PITS demo sounds very good. I just changed the sample rate to 16k, but the fundamental frequency change of synthesized speech and training corpus is quite different, even when using sentences in t…
-
We know that Stochastic Duration Prediction is used to synthesize speech with different pitches and rhythms. And how we can get duration of each phoneme.
-
**Issue:** Our current design only has a fixed rhythm (evenly spaced notes)
**Solution:** This can be remedied by using MIDI to control timings.
**Desired Input:** MIDI Input (.mid), Syllable Au…
-
# Prosody Naturalness
## Task Objective
Evaluate the prosodic understanding level of the models. The task is part of the metatask #140.
## Datasets and Evaluation Metric
### General idea
- De…
-
I want to know that this model is just to learn the rhythm of the statement you provide instead of the tone. Can I use this model to imitate the tone of his speech with a single sentence?
-
# Text-to-Speech Synthesis
Text-to-Speech is a speech generation task that converts written language into its spoken form.
## Task Objective
Text-to-Speech Synthesis (TTS) is an essential ta…
-
We have further improved AutoVC in 2 subsequent works.
The 1st work improves the audio quality by removing any pitch artifacts.
F0-consistent many-to-many non-parallel voice conversion via condi…