Qianyu Mai

Qianyu Mai

Auto-generated profile, based on publicly available information

Qianyu Mai

School of computer science and engineering, North Minzu University, Yinchuan, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2024 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
QLQiang Li
Qiang Li
QMQianyu Mai
Qianyu Mai
MWMandou Wang
Mandou Wang
MMmingjuan Ma
mingjuan Ma
As a multi-ethnic country with a large population, China is endowed with diverse dialects, which brings considerable challenges to speech recognition work. In fact, due to geographical location, population migration, and other factors, the research progress and practical application of Chinese dialect speech recognition are currently at different stages. Therefore, exploring the significant regional heterogeneities in specific recognition approaches and effects, dialect corpus, and other resources is of vital importance for Chinese speech recognition work. Based on this, we first start with the regional classification of dialects and analyze the pivotal acoustic characteristics of dialects, including specific vowels and tones patterns. Secondly, we comprehensively summarize the existing dialect phonetic corpus in China, which is of some assistance in exploring the general construction methods of dialect phonetic corpus. Moreover, we expound on the general process of dialect recognition. Several critical dialect recognition approaches are summarized and introduced in detail, especially the hybrid method of Artificial Neural Network (ANN) combined with the Hidden Markov Model(HMM), as well as the End-to-End (E2E). Thirdly, through the in-depth comparison of their principles, merits, disadvantages, and recognition performance for different dialects, the development trends and challenges in dialect recognition in the future are pointed out. Finally, some application examples of dialect speech recognition are collected and discussed.

17 October 2023
Verified
Conference Paper
Open access
QLQiang Li
Qiang Li
ZZZhibo Zhang
Zhibo Zhang
ZLZijin Liu
Zijin Liu
QMQianyu Mai
Qianyu Mai
WQWenxia Qiao
Wenxia Qiao
MMmingjuan Ma
mingjuan Ma
In the collaboration scenario, video calls can not only improve the understanding of the collaborative conversation content but also assist group members in coordinating tasks reasonably and obtaining richer collaboration information. Although they can share or view the recorded call video repeatedly, with the increase in video duration or the influence of surrounding noise, the audio-visual information contained in the collaborative conversation becomes more complex and difficult to understand. So, it's a great challenge for group members to obtain information about the collaboration topic. This paper starts with the video calls in collaborative scenarios and analyzes its interpretable elements from the obtained audio-visual dialogue information. Based on the TM-CTC model (CTC Transformer) and FaceNet algorithm, we construct a framework for deep audio-visual dialogue analysis in the Collaborative Working Environment (CWE). Subsequently, according to the framework mentioned above, we build a collaborative audio-visual dialogue server that is further applied to CWEs to analyze the video calls, generate audio-visual dialogue elements, and present the results to team members. Finally, an application example is utilized to analyze the audio-visual dialogue produced in collaborative video communications. The results show that our proposed framework can improve communication efficiency in team collaboration to a certain extent.