Biography

MA Yinghao (马英浩) is a Ph.D. student in Artificial Intelligence and Music (AIM) program at Centre for Digital Music (C4DM), School of EECS, Queen Mary University of London, supervised by Dr. Emmanouil Benetos, Dr. Chris Donahue (secondary), and Prof. Simon Dixon (independent assessor). He is one of the co-founders of the Multimodal Art Projection (MAP) community. Together with his colleague, he proposed an acoustic Music undERstanding model with large-scale self-supervised Training (MERT), with more than 50k downloads on the Huggingfac page, and established a Music Audio Representation Benchmark for universaL Evaluation (MRABLE). He is also interested in music-related multimodality and developed MusiLingo, a music captioning and query response model based on the alignment of single-modality pre-trained models.

Besides, he was one of student conductors of Chinese Philharmonic Orchestra, Chinese Music Institute at Peking University (Facebook Page). He is also an advocate of charitable activities (see at other experience).

He is now seeking for a summer internship position on SSL for MIR or music-related multimodality, in order to pave the way for a human understanding of music phenomenon.

Interests

  • Music Information Retrieval (MIR)
  • Self-supervised Learning (SSL)
  • Music-related Multimodal Machine Learning
  • Audio Signal Processing

Education

  • BSc in Mathematics, 2016-2020

    School of Mathematical Science, Peking University

  • MSc in Music & Technology, 2020-2022

    School of Music, College of Fine Arts, Carnegie Mellon University

  • PhD in AI Music, 2022-2026

    School of EECS, C4DM, QMUL

Recent Publications

Quickly discover relevant content by filtering publications.

MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response

Abstract: Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and …

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

Abstract: In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction …

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCCF none

Abstract: Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale …

On the effectiveness of speech self-supervised learning for musicCCF none

Abstract: Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. …

Lyricwhiz: Robust multilingual zero-shot lyrics transcription by whispering to chatgptCCF none

Abstract: We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving …

Music Journey

CONCERT: Yuan —- Chinese Music

The second concert after COVID for. Remote technical support for recording and live streaming of concerts. Video recording TBA

CONCERT: Music & Joy from East to West

The first concert after COVI, together with PKU orchestra, PKU Chinese orchestra and PKUCMI. Video recording TBA

Surpring for Happy Children's Day

Children's Day before the end of the period, due to the epidemic 2021 spring semester holidays are moved into the winter break, near the concert students are stressed slightly tired. This egg as a Children's Day gift to everyone, wishing everyone always young and happy every day :-)

Beethoven: Serenade in D, Op.25 - 1. Entrata (Allegro) (Dizi version)

The year 2020 marks the 250th anniversary of Beethoven's birth & a memorable year. In response, the Chinese Music Institute at PKU, together with PKU Chinese orchestra, performed an excerpt of it. It is adapted as a trio for Dizi, clarinet and flute. Compared to Beethoven's rigorous masterpiece, this cheerful work is relatively playful, and I hope that it will encourage all of you to overcome the difficulties of the times while remembering the great composer.

Music Composition

Composed a Chinese transverse flute (Di) sonata (music score) which was performed in the class concert at Peking University. A core member and seminar organizer of the Peking University Music Composition Association.

Tales of the Past –A Concert of Chinese Music

Student conductor of the symphony The Family Legend: The Moon at Dawn over Lugou Bridge(video). A music player for other symphony. In charge of copywriting and music reviews.

One of the Student Conductors

Conductor in Chinese Music Institute, Peking University. Organized rehearsals of Chinese Philharmonic Orchestra and concert.

MESSENGER – A Concert Themed on Northwestern Chinese Music

A flute player in orchestra for the concert. Author of copywriting and music review.

Leader of Academic Department at CMI, PKU

Holding seminar (making presentations) on music theory, acoustic and music information retrieval.

Chinese transverse flute (Di) Certificate

Certificate of highest amateur performance level of Chinese transverse flute (Di)

Projects

*

Bridging Music & Text with Pre-trained Models for Music Captioning and QA

07/2023 – present

Supervised by Dr Emmanouil Benetos, Centre for Digital Music, Queen Mary University of London

  • Developed Music …

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

01/2023 – 06/2023

Supervised by Dr Emmanouil Benetos, Centre for Digital Music, Queen Mary University of London

  • Designing the …

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCCF none

08/2022 – 05/2023

Supervised by Dr Emmanouil Benetos, Centre for Digital Music, Queen Mary University of London

  • Built self-supervised …

A Time-Variant Reverberation Algorithm for Reverberation Enhancement Syetem

The reverberation algorithm is usually an LTI system. The room in the concert hall does not change, so the response does not change …

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCCF none

09/2021 – 07/2022 Research Assistant, Supervised by Prof. Richard Stern, Carnegie Mellon University Constructed 2-layer learnable …

Learnable Frontend for Music, Speech and Audiow

Design learnable frontends for deep learning models inspired by classic filters, multi-rate sampling & modulation.

Cover Song Detection & Evaluation of Automatic Speech Recognition

May 2020 – Aug. 2021. Beijing, CHN. Summer internship in Tencent Holdings Limited. (Beijing)

Write literature review on coversong …

Tempo Detection of Chinese Pop Music

Jun. 2020 – Sept. 2020. Beijing, CHN. Summer internship in Beijing Deepmusic Technology Co. LTD Write literature review on song …

Research & implementation of Chinese flute playing technique recognition based on machine learning

Feb. 2020 – May 2020. Beijing, CHN. One of the graduation theses that awarded the outstanding paper honor of School of Mathematical …

TONE CONTOUR REALIZATION IN SUNG CANTONESE

Nov. 2019 – Jan. 2020. Beijing, CHN. Class project, scored 92/100. Supervised by Associate prof. WANG Yunjia, department of …

Chinese instrument recognition

Mar 2019 – Jun 2019. Beijing, CHN. Research Assistant for prof. CHEN Xiaoou in Wangxuan Institute of Computer Technology at Peking …

Correspondence between Speech Melody and Pitch Contour in Sichuan Folk Song

Jul. 2019 – Sept. 2019. Rochester, NY, US. Research Assistant supervised by prof. DUAN Zhiyao, Deparment of Electronic Computer …

Blogs

Additional Notes in ICA especially for FOBI

Suppose $A=(a_1, a_2,\cdots, a_N)^t$ is a $n$ dimension vectors, you can actually carry out the PCA $S = WA$ in the following ways: …

Learning How to Write Blog

practice of displaying posts(blogs)

Other Experience

 
 
 
 
 

Teaching Assitant at CMU

ECE, CMU

Jul 2021 – Dec 2020
Algorithm engineer on music information retireval.
 
 
 
 
 

Student Assitant at Beijing International Center for Mathematical Research

BICMR, PKU

Sep 2020 – Jun 2020
Coauthor of popular mathematical science articles and promotional texts. Some published in Mathematical Culture.
 
 
 
 
 

Internship

Beijing Deepmusic Technology Co. LTD

Jun 2020 – Sep 2020
Algorithm engineer on music information retireval.
 
 
 
 
 

Speech on Campus Barrier-Free Development

Oct 2018 – Oct 2018
By the invitation of the institute of barrier-free development of THU, delivered a speech on campus barrier-free development at the international conference on barrier-free development. The speech was praised by China Disabled Persons’Federation..
 
 
 
 
 

Volunteer Teaching

Association of young volunteers, school of Mathematical Sciences

Sep 2018 – Dec 2018
Organizer, math teacher and team leader during trip.
 
 
 
 
 

Charitable Activities

Student Union, School of Mathematical Sciences

Jan 2018 – Mar 2018
Orgnized social research and publicity for the disabled with rare diseases. Jointly with Tsinghua barrier-free development research association, PKU Loving Heart club, PKU medical center Student Sunshine Love Clinic
 
 
 
 
 

Freshman Counselor

School of Mathematical Science, PKU

Sep 2017 – Aug 2018
Help Freshman students adapt to university life.
 
 
 
 
 

Volunteer Recruitment officer of PKU for Dongcheng District

Peking University Undergraduate Admission Office

Jun 2017 – Dec 2018
  • Introduce PKU to high school student and give student encouragement before college entrance examination(Chinese Gaokao)”
  • Counselor of PKU camp for excellent high school students
  • Rated as an excellent volunteer twice
 
 
 
 
 

Peorty

Apr 2017 – Present
Poetry 《半亩清芬》, English name A Long Walk to Academy, is a collection of poems written from 2011 to 2016 as well as thoughts and views on poetry and prose, etc. to express ideals, beliefs and the feelings as a teenager. These poems are plain and straightforward and are sincere feelings on growing up during life journey. ISBN-13 9787506393676. Published by Writers Publishing House.

Contact