# MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information

arXiv: https://arxiv.org/abs/2306.02263 · HTML: https://mlsanity.com/paper/2306.02263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 38 references that are in the map.
- First posted on arXiv 4 Jun 2023.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild](https://mlsanity.com/paper/1810.06990/) (2018)
- [WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking](https://mlsanity.com/paper/2201.07425/) (2022)
- [Robust Face Recognition via Multimodal Deep Face Representation](https://mlsanity.com/paper/1509.00244/) (2015)
- [Re-synchronization using the Hand Preceding Model for Multi-modal Fusion in Automatic Continuous Cued Speech Recognition](https://mlsanity.com/paper/2001.00854/) (2020)
- [A Pilot Study on Mandarin Chinese Cued Speech](https://mlsanity.com/paper/2001.00731/) (2020)

## Abstract (arXiv)

Audio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction. However, the existing available Mandarin audio-visual datasets are limited and lack the depth information. To address this issue, this work establishes the MAVD, a new large-scale Mandarin multimodal corpus comprising 12,484 utterances spoken by 64 native Chinese speakers. To ensure the dataset covers diverse real-world scenarios, a pipeline for cleaning and filtering the raw text material has been developed to create a well-balanced reading material. In particular, the latest data acquisition device of Microsoft, Azure Kinect is used to capture depth information in addition to the traditional audio signals and RGB images during data acquisition. We also provide a baseline experiment, which could be used to evaluate the effectiveness of the dataset. The dataset and code will be released at https://github.com/SpringHuo/MAVD.