English
Related papers

Related papers: Distilling a Pretrained Language Model to a Multil…

200 papers

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of…

Computation and Language · Computer Science 2026-02-25 Sachin Gopal Wani , Eric Page , Ajay Dholakia , David Ellison

In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Zhengyang Liang , Meiyu Liang , Wei Huang , Yawen Li , Zhe Xue

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…

Computation and Language · Computer Science 2025-06-25 Siyu Liang , Gina-Anne Levow

In this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-18 Dariusz Piotrowski , Renard Korzeniowski , Alessio Falai , Sebastian Cygert , Kamil Pokora , Georgi Tinchev , Ziyao Zhang , Kayoko Yanagisawa

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Machine Learning · Computer Science 2026-01-12 Pattarawat Chormai , Ali Hashemi , Klaus-Robert Müller , Grégoire Montavon

Current speech language models exceed the size and latency constraints of many deployment environments. We build compact, expressive speech generation models through layer-aligned distillation, matching hidden states, attention maps, and…

Sound · Computer Science 2025-10-23 Mohammadmahdi Nouriborji , Morteza Rohanian

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Zili Huang , Desh Raj , Paola García , Sanjeev Khudanpur

Multilingual semantic search is the task of retrieving relevant contents to a query expressed in different language combinations. This requires a better semantic understanding of the user's intent and its contextual meaning. Multilingual…

Computation and Language · Computer Science 2023-09-18 Meryem M'hamdi , Jonathan May , Franck Dernoncourt , Trung Bui , Seunghyun Yoon

Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-08 Genshun Wan , Tan Liu , Hang Chen , Jia Pan , Cong Liu , Zhongfu Ye

Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve…

Computation and Language · Computer Science 2025-01-28 Huaixia Dou , Xinyu Tian , Xinglin Lyu , Jie Zhu , Junhui Li , Lifan Guo

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…

Computation and Language · Computer Science 2022-12-06 Ankita Pasad , Ju-Chieh Chou , Karen Livescu

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success…

Computation and Language · Computer Science 2022-04-29 Heng-Jui Chang , Shu-wen Yang , Hung-yi Lee

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

Computation and Language · Computer Science 2023-11-14 Fatema Hasan , Yulong Li , James Foulds , Shimei Pan , Bishwaranjan Bhattacharjee

It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models…

Computation and Language · Computer Science 2019-06-27 Zhenchuan Yang , Chun Zhang , Weibin Zhang , Jianxiu Jin , Dongpeng Chen

This paper describes a novel knowledge distillation framework that leverages acoustically qualified speech data included in an existing training data pool as privileged information. In our proposed framework, a student network is trained…

Sound · Computer Science 2021-12-17 Tohru Nagano , Takashi Fukuda , Gakuto Kurata

Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use…

Computation and Language · Computer Science 2020-05-06 Subhabrata Mukherjee , Ahmed Awadallah

Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) systems. Since it is impractical to use large pre-trained models…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-03 Xiaoyu Yang , Qiujia Li , Philip C. Woodland

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Jing Yang , Xiatian Zhu , Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker…

Computation and Language · Computer Science 2025-04-03 Lingwei Meng , Shujie Hu , Jiawen Kang , Zhaoqing Li , Yuejiao Wang , Wenxuan Wu , Xixin Wu , Xunying Liu , Helen Meng

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…

Computation and Language · Computer Science 2026-02-10 Ziyang Cheng , Yuhao Wang , Heyang Liu , Ronghua Wu , Qunshan Gu , Yanfeng Wang , Yu Wang