Speech/Audio Generation Researcher

ANUTTACON PTE. LTD.; Singapore; On-site; SGD 70,000 - 120,000; Full time

Job summary

A tech-focused company in Singapore is seeking an experienced professional to conduct cutting-edge research in speech and audio foundation models. The role involves designing, developing, and evaluating generative models, including multimodal approaches. Candidates should hold a Bachelor's degree in a related field and possess over 3 years of experience in machine learning and deep learning, specifically in speech and audio generation. Strong communication skills are essential for this innovative position.

Qualifications

• 3+ years experience in machine learning and deep learning.
• Experience with speech/audio generation and large language models.
• Strong communication and presentation skills.

Responsibilities

• Conduct research in speech/audio foundation models.
• Develop generative models integrating speech, text, and video.
• Implement reinforcement learning techniques for model optimization.

Skills

Machine learning

Deep learning

Speech generation

Audio generation

Generative models

Education

Bachelor degree in computer science or related field

Job description

Key Responsibilities:

• Conduct cutting-edge research and development in speech/audio foundation models.
• Research, design, develop, and evaluate generative models, including multimodal approaches integrating speech, text, and video.
• Conduct research to integrate Large Language Models (LLMs) into speech and audio generation (Neural Tokenizers, Large Language Modeling, etc.).
• Explore and implement Reinforcement Learning (RL) techniques for optimizing generative models in speech and audio applications.
• Design and curate large-scale, high-quality multimodal datasets in collaboration with cross-functional teams.

Qualifications:

• Bachelor degree in computer science, mathematics, engineering, a related field, or equivalent professional experience.
• 3+ years of experience in one or more areas of machine learning and deep learning, including but not limited to:
• Speech/Vocal generation (including text-to-speech, singing-voice-synthesis, prosody transfer, etc.)
• Audio generation (including text-to-music, etc.)
• Large scale speech/audio self-supervised representation learning and foundation models
• Large Language Model pre-training and fine-tuning
• Deep knowledge of deep learning and generative models (Diffusion, Flow Matching, AR Transformer, Mamba, VAE, GAN, etc.).
• Self-driven, innovative, collaborative, with strong communication and presentation skills.