English
Related papers

Related papers: Sounding Like a Winner? Prosodic Differences in Po…

200 papers

Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech…

Sound · Computer Science 2024-01-31 Jiatong Shi , Hirofumi Inaguma , Xutai Ma , Ilia Kulikov , Anna Sun

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-06 Kuo-Hsuan Hung , Szu-wei Fu , Huan-Hsin Tseng , Hsin-Tien Chiang , Yu Tsao , Chii-Wann Lin

Preserving a patient's identity is a challenge for automatic, speech-based diagnosis of mental health disorders. In this paper, we address this issue by proposing adversarial disentanglement of depression characteristics and speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-08 Vijay Ravi , Jinhan Wang , Jonathan Flint , Abeer Alwan

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

Sound · Computer Science 2026-04-24 Ryan Whetten , Titouan Parcollet , Marco Dinarelli , Yannick Estève

Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing…

cmp-lg · Computer Science 2007-05-23 I. Dan Melamed

Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-06 Yi-Cheng Lin , Tzu-Quan Lin , Hsi-Che Lin , Andy T. Liu , Hung-yi Lee

While there has been significant progress towards modelling coherence in written discourse, the work in modelling spoken discourse coherence has been quite limited. Unlike the coherence in text, coherence in spoken discourse is also…

Computation and Language · Computer Science 2021-01-05 Rajaswa Patil , Yaman Kumar Singla , Rajiv Ratn Shah , Mika Hama , Roger Zimmermann

Self-supervised learning (SSL) achieves great success in monaural speech enhancement, while the accuracy of the target speech estimation, particularly for unseen speakers, remains inadequate with existing pre-tasks. As speech signal…

Sound · Computer Science 2022-06-13 Yi Li , ShuangLin Li , Yang Sun , Syed Mohsen Naqvi

Prominences and boundaries are the essential constituents of prosodic structure in speech. They provide for means to chunk the speech stream into linguistically relevant units by providing them with relative saliences and demarcating them…

Computation and Language · Computer Science 2015-10-08 Antti Suni , Daniel Aalto , Martti Vainio

Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such…

Machine Learning · Computer Science 2023-06-09 Eklavya Sarkar , Mathew Magimai. -Doss

English proficiency assessments have become a necessary metric for filtering and selecting prospective candidates for both academia and industry. With the rise in demand for such assessments, it has become increasingly necessary to have the…

Computation and Language · Computer Science 2021-12-01 Pakhi Bamdev , Manraj Singh Grover , Yaman Kumar Singla , Payman Vafaee , Mika Hama , Rajiv Ratn Shah

This study asks how self-supervised speech models represent suprasegmental categories like Mandarin lexical tone, English lexical stress, and English phrasal accents. Through a series of probing tasks, we make layer-wise comparisons of…

Computation and Language · Computer Science 2024-08-27 Antón de la Fuente , Dan Jurafsky

Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…

Computation and Language · Computer Science 2019-07-11 Wei-Ning Hsu , David Harwath , James Glass

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-07 Bryce Irvin , Marko Stamenovic , Mikolaj Kegler , Li-Chia Yang

Prosodic phrasing is crucial to the naturalness and intelligibility of end-to-end Text-to-Speech (TTS). There exist both linguistic and emotional prosody in natural speech. As the study of prosodic phrasing has been linguistically…

Artificial Intelligence · Computer Science 2023-09-22 Rui Liu , Bin Liu , Haizhou Li

This paper explores predicting suitable prosodic features for fine-grained emotion analysis from the discourse-level text. To obtain fine-grained emotional prosodic features as predictive values for our model, we extract a phoneme-level…

Sound · Computer Science 2023-09-22 Xianhao Wei , Jia Jia , Xiang Li , Zhiyong Wu , Ziyi Wang

Masked latent prediction has emerged as a leading paradigm in self-supervised learning (SSL), especially for general audio and music representation learning. While recent methods have demonstrated strong performance, the role of the…

Sound · Computer Science 2025-08-19 Aurian Quelennec , Pierre Chouteau , Geoffroy Peeters , Slim Essid

This study investigates whether speech-based depression detection models learn depression-related acoustic biomarkers or instead rely on speaker identity cues. Using the DAIC-WOZ dataset, we propose a data-splitting strategy that controls…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-17 Hsiang-Chen Yeh , Luqi Sun , Aurosweta Mahapatra , Shreeram Suresh Chandra , Emily Mower Provost , Berrak Sisman

Voice conversion is the task to transform voice characteristics of source speech while preserving content information. Nowadays, self-supervised representation learning models are increasingly utilized in content extraction. However, in…

Sound · Computer Science 2024-05-02 Yimin Deng , Jianzong Wang , Xulong Zhang , Ning Cheng , Jing Xiao

In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-22 Anna Silnova , Themos Stafylakis , Ladislav Mosner , Oldrich Plchot , Johan Rohdin , Pavel Matejka , Lukas Burget , Ondrej Glembek , Niko Brummer