Master Thesis: Task-Aware and Robust Semantic Audio Communication
Ericsson ABSammanfattning
This opportunity involves a research thesis focused on improving communication efficiency and robustness in speech processing under constrained conditions. The role is based in Stockholm, Sweden, and is ideal for master's students in fields such as Computer Science or Electrical Engineering. The research will explore task-aware representation of speech information, comparing it with conventional methods to enhance performance and quality.Det här erbjuder vi
Opportunity to work on innovative solutions to complex problems.Collaborative environment with diverse innovators.Encouragement of diversity and inclusion within the organization.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-10-21
Beskrivning
Join our Team
About this opportunity:
Speech carries several overlapping types of information, including linguistic content, speaker identity, emotion, prosody, and acoustic characteristics. Their importance depends on the application: speech recognition relies on phonetic information, voice cloning on speaker identity, and call-centre analytics on cues such as emotion.
Conventional codecs typically compress and protect speech information uniformly, even when bandwidth is limited or the communication channel is lossy. This can waste resources preserving details that a downstream task does not need, while leaving less capacity for information that matters.
This thesis will investigate whether knowledge of the target task can improve communication efficiency and robustness. Possible approaches include learned representations, non-uniform bit allocation, and differentiated error protection. The goal is to prioritize task-relevant speech information while maintaining acceptable reconstructed speech quality.
Research Question
Can task-aware representation and protection of speech information improve robustness under constrained communication conditions while maintaining acceptable reconstructed speech quality?
What you will do:
The skills you bring:
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 791813
About this opportunity:
Speech carries several overlapping types of information, including linguistic content, speaker identity, emotion, prosody, and acoustic characteristics. Their importance depends on the application: speech recognition relies on phonetic information, voice cloning on speaker identity, and call-centre analytics on cues such as emotion.
Conventional codecs typically compress and protect speech information uniformly, even when bandwidth is limited or the communication channel is lossy. This can waste resources preserving details that a downstream task does not need, while leaving less capacity for information that matters.
This thesis will investigate whether knowledge of the target task can improve communication efficiency and robustness. Possible approaches include learned representations, non-uniform bit allocation, and differentiated error protection. The goal is to prioritize task-relevant speech information while maintaining acceptable reconstructed speech quality.
Research Question
Can task-aware representation and protection of speech information improve robustness under constrained communication conditions while maintaining acceptable reconstructed speech quality?
What you will do:
- Review research on learned speech representations, semantic and task-aware audio communication, and robustness.
- Select suitable audio-related tasks and speech representations for investigation.
- Explore methods for prioritizing or protecting task-relevant speech information.
- Compare task-aware and conventional approaches in terms of task performance, robustness, communication efficiency, reconstructed speech quality, and computational complexity.
The skills you bring:
- You are pursuing a master's degree, preferably in Computer Science, Electrical Engineering, Engineering Physics, or a related field.
- Coursework in signal processing and machine learning is essential.
- You have good programming skills in MATLAB, C, or Python.
- You are proficient in English.
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 791813
Ansök till tjänsten
Master Thesis: Task-Aware and Robust Semantic Audio Communication
OM FÖRETAGET
Ericsson AB
