Tiantian Feng
@tiantiaf.bsky.social
Ph.D. Postdoc@USC | Best USC Viterbi RA | Ex-intern@ Amazon, Meta | Interests: Human understanding, trustworthy computing, speech, multimodal, and wearable sensing | Love sports and music.
Reposted by Tiantian Feng
Tiantian Feng, et al.: Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits https://arxiv.org/abs/2505.14648 https://arxiv.org/pdf/2505.14648 https://arxiv.org/html/2505.14648
May 21, 2025 at 6:02 AM
Tiantian Feng, et al.: Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits https://arxiv.org/abs/2505.14648 https://arxiv.org/pdf/2505.14648 https://arxiv.org/html/2505.14648
Looking to design a better TTS and wondering how to enrich your dataset with more speaking styles (e.g. accent, emotion)? Check out my latest work: Vox-Profile (huggingface.co/papers/2505....).
Many models are available: github.com/tiantiaf0627...
Happy to connect! (My very first post here! 😜)
Many models are available: github.com/tiantiaf0627...
Happy to connect! (My very first post here! 😜)
Paper page - Vox-Profile: A Speech Foundation Model Benchmark for Characterizing
Diverse Speaker and Speech Traits
Join the discussion on this paper page
huggingface.co
May 23, 2025 at 4:45 AM
Looking to design a better TTS and wondering how to enrich your dataset with more speaking styles (e.g. accent, emotion)? Check out my latest work: Vox-Profile (huggingface.co/papers/2505....).
Many models are available: github.com/tiantiaf0627...
Happy to connect! (My very first post here! 😜)
Many models are available: github.com/tiantiaf0627...
Happy to connect! (My very first post here! 😜)