TTS
Text-to-Speech
Building a Chinese (Mandarin) Text-to-Speech System Using Bert-VITS2
Development of a Mandarin TTS system using Bert-VITS2 framework with AISHELL-3 dataset
Boxuan Lyu - Tokyo Institute of Technology
3 min
Research
VoicePing benchmarks, methodology, model evaluations, and product research.
55 articles
Speaker Diarization
Pyannote
Speaker Diarization Performance Evaluation: Pyannote.audio vs Nvidia Nemo and Post-Processing with GPT-4
Comparative evaluation of speaker diarization frameworks with DER analysis and real-time application development
Taishin Maeda - Waseda University
5 min
Pronunciation
Speech Analysis
Detecting Syllable-Level Pronunciation Stress with A Self-Attention Model
Self-attention model for identifying stress levels in spoken English syllables
Wang Weiying and Nakajima Akinori
2 min
Machine Translation
In-Context Learning
Improving In-Context Learning Performance in Machine Translation
Using TF-IDF retrieval to improve GPT-4 translation with better in-context learning examples
Chen Yufeng - Waseda University
3 min
ASR
Whisper
Training, Evaluation and Deployment of Popular Large Language Models in Automatic Speech Recognition
Research on ASR LLM fine-tuning, speaker diarization, and model comparison
Linchuan Du - The University of British Columbia
19 min
ASR
Whisper
Fine-Tuning ASR Models for Japanese and Vietnamese
Research on fine-tuning OpenAI Whisper and Azure Speech Studio for Vietnamese and Japanese speech recognition
Vikas Reddy - University of Maryland
9 min
Try VoicePing for Free
Experience communication beyond language barriers with real-time voice translation
Get Started Free