Skip to content
View ag027592's full-sized avatar
🏠
Open to speech AI / research scientist roles
🏠
Open to speech AI / research scientist roles

Organizations

@usc-sail

Block or report ag027592

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. EMO-SUPERB EMO-SUPERB Public

    EMO-SUPERB: a reproducible speech emotion recognition benchmark with leakage-free splits for 6 datasets and 15 speech SSL models (IEEE SLT 2024)

    Python 51 1

  2. cgm-contingency-scoring cgm-contingency-scoring Public

    HITL Streamlit platform for bilingual contingency scoring of CGM interview answers (synthetic demo data only)

    Python

  3. rtmri-speech-enhancement rtmri-speech-enhancement Public

    Interactive demo: evaluating modern speech enhancement on real-time MRI speech (JASA manuscript in preparation)

    HTML

  4. Do-You-Hear-What-I-Mean Do-You-Hear-What-I-Mean Public

    Project page for "Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-to-Speech Systems" (ICASSP 2026)

    JavaScript

  5. TaigiSpeech TaigiSpeech Public

    Offline local recording app used to collect TaigiSpeech, a real-world Taiwanese Hokkien speech intent dataset for eldercare voice assistants (INTERSPEECH 2026 long paper)

    JavaScript

  6. Embracing-Multi-Label Embracing-Multi-Label Public

    All-inclusive aggregation rule for multi-label speech emotion recognition: keep every annotator rating instead of collapsing to a consensus label (IEEE SLT 2024)

    Python