English
Related papers

Related papers: TRILLsson: Distilled Universal Paralinguistic Spee…

200 papers

Today, transformer language models serve as a core component for majority of natural language processing tasks. Industrial application of such models requires minimization of computation time and memory footprint. Knowledge distillation is…

Computation and Language · Computer Science 2022-05-06 Alina Kolesnikova , Yuri Kuratov , Vasily Konovalov , Mikhail Burtsev

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently…

Computation and Language · Computer Science 2024-06-17 Hancheol Park , Soyeong Jeong , Sukmin Cho , Jong C. Park

Knowledge distillation is one of the most effective methods for model compression. Previous studies have focused on the student model effectively training the predictive distribution of the teacher model. However, during training, the…

Computation and Language · Computer Science 2026-01-29 Junseok Lee , Nahoon Kim , Sangyong Lee , Chang-Jae Chun

In large part due to their implicit semantic modeling, self-supervised learning (SSL) methods have significantly increased the performance of valence recognition in speech emotion recognition (SER) systems. Yet, their large size may often…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-20 Danilo de Oliveira , Navin Raj Prabhu , Timo Gerkmann

Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downstream tasks. To address this limitation, this paper…

Machine Learning · Computer Science 2025-04-21 Wenxuan Yang , Qingqu Wei , Chenxi Ma , Weimin Tan , Bo Yan

In this work, we propose a technique to transfer speech recognition capabilities from audio speech recognition systems to visual speech recognizers, where our goal is to utilize audio data during lipreading model training. Impressive…

Multimedia · Computer Science 2022-07-13 Hadeel Mabrouk , Omar Abugabal , Nourhan Sakr , Hesham M. Eraqi

Transformer-based speech self-supervised learning (SSL) models, such as HuBERT, show surprising performance in various speech processing tasks. However, huge number of parameters in speech SSL models necessitate the compression to a more…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-27 Kangwook Jang , Sungnyun Kim , Se-Young Yun , Hoirin Kim

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…

Computation and Language · Computer Science 2019-09-27 Iulia Turc , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

Recent studies demonstrate the effectiveness of Self Supervised Learning (SSL) speech representations for Speech Inversion (SI). However, applying SI in real-world scenarios remains challenging due to the pervasive presence of background…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-22 Saba Tabatabaee , Carol Espy-Wilson

Language models pre-trained on biomedical corpora, such as BioBERT, have recently shown promising results on downstream biomedical tasks. Many existing pre-trained models, on the other hand, are resource-intensive and computationally heavy…

Computation and Language · Computer Science 2022-09-08 Omid Rohanian , Mohammadmahdi Nouriborji , Samaneh Kouchaki , David A. Clifton

Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Yang Yu , Tao Qi , Yongfeng Huang , Qi Liu

Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval tasks. This has made distilled and dense models, due to…

Information Retrieval · Computer Science 2022-12-13 Guilherme Moraes Rosa , Luiz Bonifacio , Vitor Jeronymo , Hugo Abonizio , Marzieh Fadaee , Roberto Lotufo , Rodrigo Nogueira

Recent studies in pathology foundation models have shown that scaling training data, diversifying cancer types, and increasing model size consistently improve their performance. However, giga-scale foundation models, which are trained on…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Yesung Cho , Sungmin Lee , Geongyu Lee , Minkyung Lee , Jongbae Park , Dongmyung Shin

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Computation and Language · Computer Science 2025-11-25 Alfredo Garrachón Ruiz , Tomás de la Rosa , Daniel Borrajo

Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have…

Information Retrieval · Computer Science 2025-05-19 Simon Lupart , Mohammad Aliannejadi , Evangelos Kanoulas

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 utterance-level speech representation can be used in speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-11 Jaejin Cho , Jes'us Villalba , Laureano Moro-Velazquez , Najim Dehak

Recent research has found that knowledge distillation can be effective in reducing the size of a network and in increasing generalization. A pre-trained, large teacher network, for example, was shown to be able to bootstrap a student model…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Hyun Seung Lee , Christian Wallraven

Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact…

Computation and Language · Computer Science 2023-02-28 Mengnan Du , Subhabrata Mukherjee , Yu Cheng , Milad Shokouhi , Xia Hu , Ahmed Hassan Awadallah

Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to address this with end-to-end Speech Large Language Models…

Computation and Language · Computer Science 2024-10-04 William Held , Ella Li , Michael Ryan , Weiyan Shi , Yanzhe Zhang , Diyi Yang