Kalvin Chang's picture

12 2 1

Kalvin Chang

kalbin

·

https://kalvinchang.github.io

AI & ML interests

speech, nlp, computational linguistics

Recent Activity

upvoted a paper 15 days ago

PRiSM: Benchmarking Phone Realization in Speech Models

authored a paper 17 days ago

PRiSM: Benchmarking Phone Realization in Speech Models

authored a paper 24 days ago

Towards Comprehensive Semantic Speech Embeddings for Chinese Dialects

View all activity

Organizations

New activity in kalbin/yubao_sites 24 days ago

Add paper link, GitHub link, and task category

#1 opened 25 days ago by

New activity in kalbin/yubao_videos 24 days ago

Add dataset description, paper/code links, and task categories

#2 opened 25 days ago by

New activity in microsoft/Phi-4-multimodal-instruct about 1 month ago

how to input a video?

#16 opened 11 months ago by

New activity in INK-USC/riddle_sense 2 months ago

Convert dataset to Parquet

#3 opened 2 months ago by

New activity in allenai/social_i_qa 3 months ago

test set is available

#5 opened 3 months ago by

New activity in ybisk/piqa 3 months ago

Test set

#13 opened 3 months ago by

New activity in ybisk/piqa 4 months ago

Convert dataset to Parquet

#12 opened 6 months ago by

New activity in espnet/simpleoier_librispeech_asr_train_asr_conformer7_wavlm_large_raw_en_bpe5000_sp over 2 years ago

Filepath seems to be hardcoded?

#1 opened almost 3 years ago by

New activity in Padomin/coraal-asr almost 3 years ago

Purpose of this model

#1 opened almost 3 years ago by

New activity in vitouphy/wav2vec2-xls-r-300m-timit-phoneme over 3 years ago

Segmenting output by phone

#2 opened over 3 years ago by

New activity in facebook/wav2vec2-xlsr-53-espeak-cv-ft over 3 years ago

Demo does not work

#1 opened over 3 years ago by

New activity in vitouphy/wav2vec2-xls-r-300m-timit-phoneme over 3 years ago

dx phoneme

#1 opened over 3 years ago by

dx phoneme

#1 opened over 3 years ago by