8 papers
MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models
Manh Luong, Tamas Abraham, Junae Kim +6
Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text. We introduce MCBench,…
Efficient and High-Fidelity Omni Modality Retrieval
Chuong Huynh, Manh Luong, Abhinav Shrivastava
Multimodal retrieval is the task of aggregating information from queries across heterogeneous modalities to retrieve desired targets. State-of-the-art multimodal retrieval models c…
Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
Manh Luong, Khai Nguyen, Dinh Phung +2
Audio captioning systems face a fundamental challenge: teacher-forcing training creates exposure bias that leads to caption degeneration during inference. While contrastive methods…
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
Manh Luong, Khai Nguyen, Nhat Ho +3
The Learning-to-match (LTM) framework proves to be an effective inverse optimal transport approach for learning the underlying ground metric between two sources of data, facilitati…
Federated Few-shot Learning for Cough Classification with Edge Devices
Ngan Dao Hoang, Dat Tran-Anh, Manh Luong +2
Automatically classifying cough sounds is one of the most critical tasks for the diagnosis and treatment of respiratory diseases. However, collecting a huge amount of labeled cough…
A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation
Linh The Nguyen, Nguyen Luong Tran, Long Doan +2
In this paper, we introduce a high-quality and large-scale benchmark dataset for English-Vietnamese speech translation with 508 audio hours, consisting of 331K triplets of (sentenc…
FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesis
Manh Luong, Viet Anh Tran
Recently, autoregressive neural vocoders have provided remarkable performance in generating high-fidelity speech and have been able to produce synthetic speech in real-time. Howeve…
Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder
Manh Luong, Viet Anh Tran
Voice conversion is a challenging task which transforms the voice characteristics of a source speaker to a target speaker without changing linguistic content. Recently, there have…