.. samples-xin documentation master file, created by
   sphinx-quickstart on Sun Apr 25 22:58:24 2021.
   You can adapt this file completely to your liking, but it should at least
   contain the root `toctree` directive.

.. _label-nsf-v3:

Hn-sinc-NSF
***********

Messages
--------

	* Paper:

	    Wang, X. & Yamagishi, J. Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis. in Proc. SSW 1–6 (ISCA, 2019). `doi:10.21437/SSW.2019-1 <http://dx.doi.org/10.21437/SSW.2019-1>`__

	* BibTex::

	    @inproceedings{Wang2019,
	    address = {ISCA},
	    author = {Wang, Xin and Yamagishi, Junichi},
	    booktitle = {Proc. SSW},
	    doi = {10.21437/SSW.2019-1},
	    pages = {1--6},
	    publisher = {ISCA},
	    title = {{Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis}},
	    url = {http://www.isca-speech.org/archive/SSW{\_}2019/abstracts/SSW10{\_}O{\_}1-1.html},
	    year = {2019}
	    }

	* Experiments were based on ATR-Ximera F009 voice (Japanese, commercial database)


	* Code is available. You need both the `CURRENNT toolkit <https://github.com/nii-yamagishilab/project-CURRENNT-public>`_ and `scripts <https://github.com/nii-yamagishilab/project-CURRENNT-scripts>`_. `This subfolder <https://github.com/nii-yamagishilab/project-CURRENNT-scripts/tree/master/waveform-modeling/project-NSF-v2-pretrained>`_ in the script repository is for this project

	* New implementaion based on Pytorch is also `available <https://github.com/nii-yamagishilab/project-NN-Pytorch-scripts>`_;

	* Slides for SSW 2019 presentation can be found on `this page <https://tonywangx.github.io/slide.html>`_. You may also directly download the `PDF <https://www.dropbox.com/sh/gf3zp00qvdp3row/AABEVzUUqnJ4QbkxiQcjOhM5a/web/2019-ssw.pdf?raw=1>`__;

	* Note that

		Copy-synthesis refers to waveform generation given natural acoustic features

		Text-to-speech refers to waveform generation given acoustic features predicted from the text input
		
|

Audio samples
-------------
Natural waveform samples cannot be released online due to the license issue.


.. raw:: html

	 	<b>Utterance: _AOZORAR_09534_T01</b>
	    <br><table border="1">
	    <td colspan="6"></td>
		<tr>
		  <th>Mel-spec. + F0 (15-hr data)</th><th>WaveNet</th><th>hn-NSF</th><th>h-sinc1-NSF</th><th>h-sinc2-NSF</th><th>h-sinc3-NSF</th>
		</tr>
		<tr>
	          <td>Copy-synthesis:</td>
	          <td><audio controls><source src="./jp-v2/WELV_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELV_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C1V_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2V_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3V_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>	  
	 	</tr>
		<tr>
	          <td>Text-to-speech:</td>
	          <td><audio controls><source src="./jp-v2/WELS_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELS_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C1S_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2S_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3S_ATR_Ximera_F009_AOZORAR_09534_T01.wav"></audio></td>
	 	</tr>
	    </table>
	    <hr>
	    <br>
	    <br>
	    <b>Utterance: _AOZORAR_03372_T01</b>
	    <table border="1">
	    <td colspan="6"></td>
		<tr>
	          <th>Mel-spec. + F0 (15-hr data)</th><th>WaveNet</th><th>hn-NSF</th><th>h-sinc1-NSF</th><th>h-sinc2-NSF</th><th>h-sinc3-NSF</th>
		</tr>
		<tr>
	          <td>Copy-synthesis:</td>
	          <td><audio controls><source src="./jp-v2/WELV_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELV_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1V_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2V_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3V_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
	 	</tr>
		<tr>
	          <td>Text-to-speech:</td>
	          <td><audio controls><source src="./jp-v2/WELS_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELS_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1S_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2S_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3S_ATR_Ximera_F009_AOZORAR_03372_T01.wav"></audio></td>
	 	</tr>
	    </table>
	    <br>
	    <b>Utterance: _NIKKEIR_03132_T01</b>
	    <br><table border="1">
	    <td colspan="6"></td>
		<tr>
	          <th>Mel-spec. + F0 (15-hr data)</th><th>WaveNet</th><th>hn-NSF</th><th>h-sinc1-NSF</th><th>h-sinc2-NSF</th><th>h-sinc3-NSF</th>
		</tr>
		<tr>
	          <td>Copy-synthesis:</td>
	          <td><audio controls><source src="./jp-v2/WELV_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELV_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1V_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2V_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3V_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
	 	</tr>
		<tr>
	          <td>Text-to-speech:</td>
	          <td><audio controls><source src="./jp-v2/WELS_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELS_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1S_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2S_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3S_ATR_Ximera_F009_NIKKEIR_03132_T01.wav"></audio></td>
	 	</tr>
	    </table>
	    <hr>
	    <br>
	    <b>Utterance:  _NIKKEIR_00257_T01</b>
	    <table border="1">
	    <td colspan="6"></td>
		<tr>
	          <th>Mel-spec. + F0 (15-hr data)</th><th>WaveNet</th><th>hn-NSF</th><th>h-sinc1-NSF</th><th>h-sinc2-NSF</th><th>h-sinc3-NSF</th>
		</tr>
		<tr>
	          <td>Copy-synthesis:</td>
	          <td><audio controls><source src="./jp-v2/WELV_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELV_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1V_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C2V_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C3V_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	 	</tr>
		<tr>
	          <td>Text-to-speech:</td>
	          <td><audio controls><source src="./jp-v2/WELS_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELS_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1S_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C2S_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C3S_ATR_Ximera_F009_NIKKEIR_00257_T01.wav"></audio></td>
	 	</tr>
	    </table>
	    <hr>
	    <br>
	    <br>
	    <b>Utterance: _BTEC_00312_T01</b>
	    <br><table border="1">
	    <td colspan="6"></td>
		<tr>
	          <th>Mel-spec. + F0 (15-hr data)</th><th>WaveNet</th><th>hn-NSF</th><th>h-sinc1-NSF</th><th>h-sinc2-NSF</th><th>h-sinc3-NSF</th>
		</tr>
		<tr>
	          <td>Copy-synthesis:</td>
	          <td><audio controls><source src="./jp-v2/WELV_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELV_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1V_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2V_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3V_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
	 	</tr>
		<tr>
	          <td>Text-to-speech:</td>
	          <td><audio controls><source src="./jp-v2/WELS_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v2/IELS_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
	          <td><audio controls><source src="./jp-v3/C1S_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C2S_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
		  <td><audio controls><source src="./jp-v3/C3S_ATR_Ximera_F009_BTEC_00312_T01.wav"></audio></td>
	 	</tr>
	    </table>


.. toctree::
   :hidden:
   :maxdepth: 1