How Volcano Engine and CAS Acoustic Institute Won Top Spots at the First Low‑Resource Audio Codec Challenge

Volcano Engine's audio team, together with the Chinese Academy of Sciences Acoustic Institute, secured first‑place, runner‑up, and third‑place finishes in the 2025 Low‑Resource Audio Codec Challenge at ICASSP 2026 by delivering AI‑driven codecs that balance ultra‑low bitrate, low complexity, and high audio quality for real‑time communication and streaming scenarios.

AI codecICASSPVolcano Engine

0 likes · 12 min read

How Volcano Engine and CAS Acoustic Institute Won Top Spots at the First Low‑Resource Audio Codec Challenge

DataFunSummit

Jan 6, 2025 · Artificial Intelligence

Efficient Large‑Model Training with LLaMA‑Factory: Overview, Techniques, and Applications

This article explains how to train large language models efficiently using LLaMA‑Factory, covering low‑resource training challenges, memory‑saving optimizations for parameters, gradients and activations, framework features, quick‑start guidance, performance tuning, real‑world case studies, and a detailed Q&A.

AIDeepSpeedLLaMA-Factory

0 likes · 10 min read

Efficient Large‑Model Training with LLaMA‑Factory: Overview, Techniques, and Applications

DataFunTalk

Jun 21, 2023 · Artificial Intelligence

Low‑Resource NLP Pretraining: Methodology, Experiments, and Zero‑Shot Applications

This article presents a low‑resource NLP pretraining approach that combines transformer‑based language modeling with contrastive vector learning, details the unsupervised sample‑pair construction, introduces a camel‑shaped masking distribution, and demonstrates through extensive experiments that the resulting model achieves strong zero‑shot NLU, NLG, and retrieval performance while requiring minimal compute and data.

Language Modelingcontrastive learninglow-resource

0 likes · 10 min read

Low‑Resource NLP Pretraining: Methodology, Experiments, and Zero‑Shot Applications

DataFunTalk

Nov 5, 2019 · Artificial Intelligence

Low-Resource Text-to-Speech: FastSpeech, LightTTS, and LightBERT Overview

This article reviews recent advances in low‑resource text‑to‑speech synthesis, covering the background of TTS, challenges in data‑ and compute‑limited scenarios, and detailed descriptions of FastSpeech, LightTTS, LightBERT, and related lightweight vocoder techniques, along with experimental results and future research directions.

FastSpeechLightTTSlow-resource

0 likes · 20 min read

Low-Resource Text-to-Speech: FastSpeech, LightTTS, and LightBERT Overview