Published:
Decoding intended speech from intracortical neural signals using a Dual-Stream GRU-Conformer that encodes spike count and spike band power independently, achieving 9.38% WER on Brain-to-Text Benchmark ‘24.
Published:
This project is customized to use the latest ASR model Whisper-large, with additional implementation of a React UI and several other signal processing tweaks.. .
Published:
FastSpeechStyle : Vietnamese Emotional Speech Synthesis for VLSP 2022 Shared Task. VLSP is the most prestigious and quality contest in Vietnam for speech and natural language processing, I was fortunate to join talented colleagues at Vinbigdata and won two first prizes. 
Published:
Fake synthetic speech audio tracks can be generated through a wide variety of available methods. Given an audio recording representing a synthetically generated speech track, to detect which method among a list of candidate ones has been used to synthesize the speech. 
Published:
Sing any song without speaking the language 
Published:
Speech Translation for Low Resource Language with Voice I/O and Preserve the Characteristics of the Voice Input 
Published:
Sleep stage classification refers to the process of categorizing different stages of sleep based on the patterns and characteristics of brain activity.
Published:
Pypi Package Viphoneme: Phonetization, Convert Vietnamese Grapheme to IPA. I did this project in my 3rd year of college, which converts raw text to phonemes of sound so that speech AI models can learn, this package is accessible and used by most projects Voice research project in Vietnam (not production) 
Published:
Python - NSW package for Vietnamese: Normalization system to convert numbers, abbreviations, and words that cannot be pronounced into syllables. I worked on this project at AILAB with an outstanding friend in APCS Program. Originally written in C++ then packaged into python for ease of use in research projects 
Published:
This is the AI Service Core system design for virtual assistants I made during my internship in my 3rd year of university. 
Published:
This is the test statistics of the Rasa chatbot system I made during my 3rd year internship 
Published:
This report aim to analyze the performance of Voice of Southern TTS system and take an overview about Vietnamese TTS. Some statistics and improvements for Frontend of VOS are also given based on the popular syllables nowadays.
Published:
We utilize the natural structure of a song which is words combine to lines, lines combine to segments, and segments combine to a complete song by adapting a hierarchical attention networks (HAN). .
Published:
Technology is growing rapidly, especially the explosion of artificial intelligence in recent years has raised many concerns about the danger of the development itself 
Published:
CUDA is architecture and programming model developed by NVIDIA to run parallel computing on graphics processing units (GPUs) CUDA is the acronym for Compute Unified Device Architecture 