1 citations · 1 across the 12 of their papers we have counts for
15 papers
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System
Thomas Thebaud, Sonal Joshi, Henry Li +4
Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a speech commands classificatio…
Beyond Transcripts: Iterative Peer-Editing with Audio Unlocks High-Quality Human Summaries of Conversational Speech
Kaavya Chaparala, Thomas Thebaud, Jesús Villalba López +3
There are not enough established benchmarks for the task fo speech summarization. Creating new benchmarks demands human annotation, as LLMs could embed systemic errors and bias int…
Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization
Yen-Ju Lu, Kunxiao Gao, Mingrui Liang +5
Recent audio language models can follow long conversations. However, research on emotion-aware or spoken dialogue summarization is constrained by the lack of data that links speech…
Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams
Xiluo He, Alexander Polok, Jesús Villalba +2
An increasingly common training paradigm for multi-talker automatic speech recognition (ASR) is to use speaker activity signals to adapt single-speaker ASR models for overlapping s…
Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation
Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velazquez +2
We present Paired by the Teacher (PbT), a two-stage teacher-student pipeline that synthesizes accurate input-output pairs without human labels or parallel data. In many low-resourc…
Cross-Corpus and Cross-domain Handwriting Assessment of NeuroDegenerative Diseases via Time-Series-to-Image Conversion
Gabrielle Chavez, Laureano Moro-Velazquez, Ankur Butala +2
Handwriting is significantly affected by neurological disorders (ND) such as Parkinson's disease (PD) and Alzheimer's disease (AD). Prior works have analyzed handwriting tasks usin…
Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM
Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner +2
In dialogue transcription pipelines, Large Language Models (LLMs) are frequently employed in post-processing to improve grammar, punctuation, and readability. We explore a compleme…
MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances
Junhyeok Lee, Helin Wang, Yaohan Guan +4
We introduce MaskVCT, a zero-shot voice conversion (VC) model that offers multi-factor controllability through multiple classifier-free guidances (CFGs). While previous VC models r…
Multi-Target Backdoor Attacks Against Speaker Recognition
Alexandrine Fortier, Sonal Joshi, Thomas Thebaud +3
In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approac…
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
Yen-Ju Lu, Jing Liu, Thomas Thebaud +4
We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to s…
Noise-robust Speech Separation with Fast Generative Correction
Helin Wang, Jesus Villalba, Laureano Moro-Velazquez +3
Speech separation, the task of isolating multiple speech sources from a mixed audio signal, remains challenging in noisy environments. In this paper, we propose a generative correc…
Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification
Sonal Joshi, Thomas Thebaud, Jesús Villalba +1
Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to dete…
Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning
Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velazquez +2
Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images…
DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
Helin Wang, Thomas Thebaud, Jesus Villalba +4
We present a novel typical-to-atypical voice conversion approach (DuTa-VC), which (i) can be trained with nonparallel data (ii) first introduces diffusion probabilistic model (iii)…
Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez +2
Speech super-resolution/Bandwidth Extension (BWE) can improve downstream tasks like Automatic Speaker Verification (ASV). We introduce a simple novel technique called Self-FiLM to…