19 citations · 29 across the 27 of their papers we have counts for
32 papers
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
Thomas Thebaud, Yuzhe Wang, Hao Zhang +5
Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these sy…
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
Thomas Thebaud, Junhyeok Lee, Laureano Moro-Velazquez +2
Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather t…
TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue
Hao Zhang, Thomas Thebaud, Georgi Tinchev +2
Turn-taking naturalness is central to full-duplex spoken dialogue systems, yet its automatic evaluation remains limited. Existing evaluations often rely on human judgments or behav…
TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
Sathvik Manikantan Napa Ugandhar, Hao Zhang, Alison Gunzler +5
With the proliferation of speech AI agents, understanding emotional entrainment in conversational interaction has become increasingly important. Emotional entrainment is shaped by…
Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems
Ashish Hallur, Thomas Thebaud, Georgi Tinchev +2
Speech-to-speech (S2S) AI agents are advancing rapidly, yet evaluation lacks interpretable speech-native measures for conversational prosody and rhythm. Because , speaking rat…
Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation
Thomas Thebaud, Yuzhe Wang, Laureano Moro-Velazquez +2
Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the sp…
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
Junhyeok Lee, Xiluo He, Jihwan Lee +6
Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it do…
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…
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…
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…
Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker Traits and Speech Properties
Tiantian Feng, Jihwan Lee, Anfeng Xu +9
We introduce Vox-Profile, a comprehensive benchmark to characterize rich speaker traits and speech properties using speech foundation models. Unlike prior work that targets a singl…
Automatic Proficiency Assessment in L2 English Learners
Armita Mohammadi, Alessandro Lameiras Koerich, Laureano Moro-Velazquez +1
Second language proficiency (L2) in English is usually perceptually evaluated by English teachers or expert evaluators, with the inherent intra- and inter-rater variability. This p…
Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings
Sarah Laouedj, Yuzhe Wang, Jesus Villalba +3
In this study, we explored the use of spectrograms to represent handwriting signals for assessing neurodegenerative diseases, including 42 healthy controls (CTL), 35 subjects with…
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…
Interpretable Features for the Assessment of Neurodegenerative Diseases through Handwriting Analysis
Thomas Thebaud, Anna Favaro, Casey Chen +4
Motor dysfunction is a common sign of neurodegenerative diseases (NDs) such as Parkinson's disease (PD) and Alzheimer's disease (AD), but may be difficult to detect, especially in…
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…
Improving fairness for spoken language understanding in atypical speech with Text-to-Speech
Helin Wang, Venkatesh Ravichandran, Milind Rao +8
Spoken language understanding (SLU) systems often exhibit suboptimal performance in processing atypical speech, typically caused by neurological conditions and motor impairments. R…
Time Scale Network: A Shallow Neural Network For Time Series Data
Trevor Meyer, Camden Shultz, Najim Dehak +2
Time series data is often composed of information at multiple time scales, particularly in biomedical data. While numerous deep learning strategies exist to capture this informatio…
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)…
Regularizing Contrastive Predictive Coding for Speech Applications
Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko +2
Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduc…
Stabilized training of joint energy-based models and their practical applications
Martin Sustek, Samik Sadhu, Lukas Burget +4
The recently proposed Joint Energy-based Model (JEM) interprets discriminatively trained classifier as an energy model, which is also trained as a generative model describ…
Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
Jaejin Cho, Jes'us Villalba, Laureano Moro-Velazquez +1
In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of uttera…