What all do audio transformer models hear? Probing Acoustic
Representations for Language Delivery and its Structure

What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure

2 January 2021

Yaman Kumar Singla

Papers citing "What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure"

16 / 16 papers shown

Title
Enhancing and Exploring Mild Cognitive Impairment Detection with W2V-BERT-2.0 Yueguan Wang Tatsunari Matsushima Soichiro Matsushima Toshimitsu Sakai 31 0 0 28 Jan 2025
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers Hosein Mohebbi Grzegorz Chrupała Willem H. Zuidema A. Alishahi 28 12 0 15 Oct 2023
Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition Weidong Chen Xiaofen Xing Peihao Chen Xiangmin Xu VLM 28 35 0 20 Jul 2023
Investigating Pre-trained Audio Encoders in the Low-Resource Condition Haomiao Yang Jinming Zhao Gholamreza Haffari Ehsan Shareghi 14 6 0 28 May 2023
SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing Weidong Chen Xiaofen Xing Xiangmin Xu Jianxin Pang Lan Du 30 38 0 27 Feb 2023
Phone and speaker spatial organization in self-supervised speech representations Pablo Riera M. Cerdeiro L. Pepino Luciana Ferrer SSL 16 1 0 24 Feb 2023
Comparative layer-wise analysis of self-supervised speech models Ankita Pasad Bowen Shi Karen Livescu SSL 22 109 0 08 Nov 2022
Probing Statistical Representations For End-To-End ASR A. Ollerenshaw Md. Asif Jalal Thomas Hain 19 2 0 03 Nov 2022
On the Utility of Self-supervised Models for Prosody-related Tasks Guan-Ting Lin Chiyu Feng Wei-Ping Huang Yuan Tseng Tzu-Han Lin Chen An Li Hung-yi Lee Nigel G. Ward 21 47 0 13 Oct 2022
Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning Eesung Kim J. Jeon Hyeji Seo Ho-Young Kim SSL 21 37 0 08 Apr 2022
Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees Yaman Kumar Singla Sriram Krishna R. Shah Changyou Chen 18 6 0 17 Nov 2021
Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations Hyeong-Seok Choi Juheon Lee W. Kim Jie Hwan Lee Hoon Heo Kyogu Lee 12 150 0 27 Oct 2021
AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses Yaman Kumar Singla Swapnil Parekh Somesh Singh J. Li R. Shah Changyou Chen AAML 25 13 0 24 Sep 2021
Layer-wise Analysis of a Self-supervised Speech Representation Model Ankita Pasad Ju-Chieh Chou Karen Livescu SSL 26 287 0 10 Jul 2021
Probing the Information Encoded in X-vectors Desh Raj David Snyder Daniel Povey Sanjeev Khudanpur 32 84 0 13 Sep 2019
What you can cram into a single vector: Probing sentence embeddings for linguistic properties Alexis Conneau Germán Kruszewski Guillaume Lample Loïc Barrault Marco Baroni 199 882 0 03 May 2018