Atlas / Reports / Detail
SPIrit-LM: Interleaved Spoken and Written Language Model
Speech Language Models report from Meta AI with 10 connected researchers in the LLMpeople atlas.
Connected researchers
Researcher
1 reports
Wei-Ning Hsu
Meta AI
Research scientist at Meta FAIR working on speech and audio foundation models. His research covers self-supervised learning, spoken language modeling, and multimodal audio-language systems.
Researcher
1 reports
Yossi Adi
Meta AI
Yossi Adi is a computer scientist at the Hebrew University of Jerusalem and a research scientist at Meta FAIR. His research focuses on speech, audio, and language modeling, including spoken language models and machine learning methods for speech applications.
Researcher
1 reports
Felix Kreuk
Meta AI
Research scientist at Meta AI working on generative AI, multimodal learning, and speech and audio generation. His public homepage notes earlier research at Bar-Ilan University before joining Meta in Menlo Park.
Researcher
1 reports
Tu Anh Nguyen
Meta AI
Tu Anh Nguyen is a research scientist at Meta working on speech and audio generation. He is also a PhD candidate at Mila and the Universite de Montreal, advised by Yoshua Bengio and Abdelrahman Mohamed, with interests in audio language models, speech generation, and efficient inference.
Researcher
1 reports
Emmanuel Dupoux
Meta AI
Research scientist and professor working across Meta, NYU, and EHESS on speech, language, and cognitive science. His work studies how humans and machines acquire language and how spoken and written models can be aligned.
Researcher
1 reports
Morgane Riviere
Meta AI
Research scientist working on natural language processing, with public work spanning speech and language modeling such as VoxPopuli, pGSLM, and SPIrit-LM.
Researcher
2 reports
Kushal Lakhotia
Meta AI
Research scientist at Meta whose OpenReview profile describes work on multilingual language and speech models, along with data and inference optimization.
Researcher
1 reports
Abdelrahman Mohamed
Meta AI
Abdelrahman Mohamed is a professor at the University of Toronto and a Canada CIFAR AI Chair whose work spans speech, audio, and language modeling. His public profile highlights speech recognition, representation learning, and multimodal foundation models.
Researcher
1 reports
Alexei Baevski
Meta AI
Research scientist at Meta whose public work spans speech and audio-language modeling; arXiv author results include SPIrit-LM.
Researcher
1 reports
Ariel Noy
Meta AI
Research scientist at Meta working on spoken language technology and multimodal language models.