PhD ” Advanced neural audio coding for mono and stereo signals ” F/M

Job title:

PhD ” Advanced neural audio coding for mono and stereo signals ” F/M

Company:

Orange

Job description

about the roleYour role is to carry out a PhD work on the subject: “Advanced neural coding for mono and stereo audio signals”.Overall context and problem statement
Audio compression (or audio coding) is a field that originated in source coding, with a long history marked by the development of numerous codecs, some of which are well known to the general public, such as MP3 or AAC for music transmission or storage.In recent years, the field of audio coding has been shaken up by deep learning technologies. Artificial neural networks make it possible to achieve very low compression rates.
As a result, a new generation of multimedia signal compression methods has emerged, based on deep learning. Auto-encoder architectures based on Generative Adversarial Network (GAN) learning give very good results, with codecs such as SoundStream, EnCodec, or Descript Audio Codec (DAC). Other approaches, such as diffusion models, are also being investigated.Current neural audio codecs are essentially mono. Compared with “traditional” codecs, they are generally much more complex (in terms of computational resources), requiring very significant storage (on the order of 10 to 80M parameters, for example).Scientific objective – expected outcome and challenges to be addressed
In this context, the aim of the thesis is to design and develop innovative audio coding methods based on deep learning, for mono and stereo signals.In particular, the thesis will aim to address the following challenges:

• Obtain an audio representation by (artificial) neural networks that is capable of covering both mono and stereo
• Reduce the complexity of representation models in neural audio coding
• Obtain and interpretable latent space (giving a frequency-wise or content-wise separation)

Recent approaches such as transformers or diffusion models will be studied, and new neural network architectures will be tested and explored.Indicative list of references
1. Minje Kim and Jan Skoglund, “Neural Speech and Audio Coding,” arXiv:2408.06954v1, 20242. Thomas Muller, Stephane Ragot, Laetitia Gros, Pierrick Philippe, Pascal Scalart, Speech quality evaluation of neural audio codecs, Interspeech, 20243. N. Zeghidour et al., “SoundStream: An End-to-End Neural Audio Codec,” IEEE/ACM Trans. TASLP, 2021, arXiv:2107.033124. R. Kumar et al., “High-Fidelity Audio Compression with Improved RVQGAN,” in Advances in Neural Information Processing Systems, vol. 36, 2023.5. J.D Parker et al., Scaling Transformers for Low-Bitrate High-Quality Speech Coding, arXiv:2411.19842, Nov. 20246. Yaoxun Xu, et al., “ MuCodec: Ultra Low-Bitrate Music Codec,” arXiv:2409.13216, Sep. 2024about youSkills (scientific and technical) and personal qualities required by the position

• Solid education in mathematics (probability theory, algebra, …) and digital signal processing
• Interest in speech/audio processing
• In-depth knowledge of Python – knowledge of C and MATLAB would be a plus
• Experience in machine learning, in particular deep learning, experience with the PyTorch framework
• Rigor and creativity
• Good command of English

Required education/diploma : Research Master’s degree and/or engineering school degree (with an internship in a research lab)additional informationThe aim of the thesis is to design new audio compression methods by applying knowledge of deep learning. You will be working on generative AI and neural coding technologies that are at the cutting edge of methods used in audio signal processing. This thesis will enable you to develop expertise in machine learning methodologies, whose applications go far beyond the audio domain.You will have access to a range of equipment to help you carry out your research work, including sound capture and rendering systems for dataset creation, and centralized computing resources (a cluster with around a hundred GPUs) for work on neural networks.
The research work will be carried out in a cooperative mode with the team’s researchers and engineers, contributing to the standardization of audio codecs and writing scientific articles and patent applications. The thesis will leverage Orange’s experience in audio quality assessment (subjective testing, automatic quality measurement tools, etc.), with an internationally recognized test laboratory.departmentOrange Innovation brings together the research and innovation activities and expertise of the Group’s entities and countries. We work every day to ensure that Orange is recognized as an innovative operator by its customers and we create value for the Group and the Brand in each of our projects. With 740 researchers, thousands of marketers, developers, designers and data analysts, it is the expertise of our 6,000 employees that fuels this ambition every day.Orange Innovation anticipates technological breakthroughs and supports the Group’s countries and entities in making the best technological choices to meet the needs of our consumer and business customers.At Innovation, you will be part of a team at the cutting edge of innovation and expertise in audio signal processing. The thesis focuses on neural network audio compression, which is a very activeresearch field, with many open questions still to be explored. Neural audio compression is already integrated into certain services, results of the PhD work may be directly transferred to real-life products or services.contractThesis

Expected salary

Location

Lannion, Côtes-d’Armor

Job date

Wed, 26 Mar 2025 23:24:35 GMT

To help us track our recruitment effort, please indicate in your email/cover letter where (vacanciesin.eu) you saw this job posting.