DEVELOPMENT OF A SPEECH TRANSLATION SYSTEM WITH PARTIAL SEGMENTATION ALIGNMENT USING VISUALLY GROUNDED SPEECH MODELS
Speech-to-speech translation systems (S2ST) have been developed to bridge communication across languages. Although this technology has evolved over several decades, many systems still rely on written text. With over 7,000 languages worldwide, half lacking a written form, building a reliable S2ST...
Saved in:
Main Author: | Nurhaliza, Putri |
---|---|
Format: | Final Project |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/86171 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
Similar Items
-
Filipino to chinese speech-to-speech translator using neural network with database system
by: Bailon, Mark Renier M., et al.
Published: (2019) -
Filipino to Chinese speech-to-speech translator using neural network and database system
by: Bailon, Mark Reinier M., et al.
Published: (2012) -
Audio segmentation for speech/non-speech detection using wavelet transform
by: Swe Zin Kalayar Khine.
Published: (2008) -
Localizing Fake Segments in Speech
by: SIM MONG CHENG, TERENCE, et al.
Published: (2022) -
STRUCTURAL AMBIGUITY RESOLUTION IN INDONESIAN-ENGLISH SPEECH-TO-TEXT TRANSLATION SYSTEM BY UTILIZING PROSODIC INFORMATION OF SPEECH
by: Faradishi Widiaputri, Ruhiyah