Self-supervised Speech Representations Still Struggle with African American Vernacular English

26 August 2024

Papers citing "Self-supervised Speech Representations Still Struggle with African American Vernacular English"

7 / 7 papers shown

Title
Improving Speech Recognition for African American English With Audio Classification Shefali Garg Zhouyuan Huo K. Sim Suzan Schwartz Mason Chua ... Zion Mengesha Dongseong Hwang Tara N. Sainath Francoise Beaufays P. M. Mengibar 47 4 0 16 Sep 2023
Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration Kinan Martin Jon Gauthier Canaan Breiss R. Levy SSL 73 16 0 09 Jun 2023
Opening the Black Box of wav2vec Feature Encoder Kwanghee Choi Eunjung Yeo SSL 72 16 0 27 Oct 2022
Quantifying Language Variation Acoustically with Few Resources Martijn Bartelds Martijn B. Wieling 49 13 0 05 May 2022
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022 Takaaki Saeki Detai Xin Wataru Nakata Tomoki Koriyama Shinnosuke Takamichi Hiroshi Saruwatari 104 207 0 05 Apr 2022
Automatic Dialect Density Estimation for African American English Alexander Johnson K. Everson Vijay Ravi A. Gladney Mari Ostendorf Abeer Alwan 42 7 0 03 Apr 2022
DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors Chandan K. A. Reddy Vishak Gopal Ross Cutler 72 311 0 28 Oct 2020