English
Related papers

Related papers: Unifying Model and Layer Fusion for Speech Foundat…

200 papers

Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these approaches to Automatic Speech Recognition, we demonstrate…

Machine Learning · Computer Science 2022-02-07 Lillian Zhou , Dhruv Guliani , Andreas Kabel , Giovanni Motta , Françoise Beaufays

Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-04 Weiqing Wang , Kunal Dhawan , Taejin Park , Krishna C. Puvvada , Ivan Medennikov , Somshubra Majumdar , He Huang , Jagadeesh Balam , Boris Ginsburg

Developing effective multimodal data fusion strategies has become increasingly essential for improving the predictive power of statistical machine learning methods across a wide range of applications, from autonomous driving to medical…

Machine Learning · Computer Science 2025-07-29 Ziyi Liang , Annie Qu , Babak Shahbaba

Speech foundation models, trained on vast datasets, have opened unique opportunities in addressing challenging low-resource speech understanding, such as child speech. In this work, we explore the capabilities of speech foundation models on…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Anfeng Xu , Kevin Huang , Tiantian Feng , Lue Shen , Helen Tager-Flusberg , Shrikanth Narayanan

Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single…

Machine Learning · Computer Science 2023-09-28 Weishi Li , Yong Peng , Miao Zhang , Liang Ding , Han Hu , Li Shen

Recently, deep neural network (DNN) based time-frequency (T-F) mask estimation has shown remarkable effectiveness for speech enhancement. Typically, a single T-F mask is first estimated based on DNN and then used to mask the spectrogram of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-29 Liangchen Zhou , Wenbin Jiang , Jingyan Xu , Fei Wen , Peilin Liu

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

Computation and Language · Computer Science 2023-05-30 Chen Xu , Yuhao Zhang , Chengbo Jiao , Xiaoqian Liu , Chi Hu , Xin Zeng , Tong Xiao , Anxiang Ma , Huizhen Wang , JingBo Zhu

Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of…

Computation and Language · Computer Science 2024-06-19 Guodong Du , Jing Li , Hanting Liu , Runhua Jiang , Shuyang Yu , Yifei Guo , Sim Kuan Goh , Ho-Kin Tang

Text-Speech Language Models (TSLMs) -- language models trained to jointly process and generate text and speech -- are commonly trained through an early modality fusion/fission approach, in which both modalities are fed and predicted from a…

Computation and Language · Computer Science 2025-10-21 Santiago Cuervo , Adel Moumen , Yanis Labrak , Sameer Khurana , Antoine Laurent , Mickael Rouvier , Phil Woodland , Ricard Marxer

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-10 Philippe Gonzalez , Zheng-Hua Tan , Jan Østergaard , Jesper Jensen , Tommy Sonne Alstrøm , Tobias May

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-24 Zhepei Wang , Ritwik Giri , Devansh Shah , Jean-Marc Valin , Michael M. Goodwin , Paris Smaragdis

Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representational divergence arising from permutation invariance, random initialization, and heterogeneous…

Machine Learning · Computer Science 2026-05-29 Phoomraphee Luenam , Andreas Spanopoulos , Amit Sant , Thomas Hofmann , Sotiris Anagnostidis , Sidak Pal Singh

Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive successes on downstream tasks, we still have a limited…

Computation and Language · Computer Science 2023-03-20 Ankita Pasad , Bowen Shi , Karen Livescu

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

Computation and Language · Computer Science 2022-06-02 Bi-Cheng Yan , Hsin-Wei Wang , Shih-Hsuan Chiu , Hsuan-Sheng Chiu , Berlin Chen

Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model…

Computation and Language · Computer Science 2023-10-16 Ju-Chieh Chou , Chung-Ming Chien , Wei-Ning Hsu , Karen Livescu , Arun Babu , Alexis Conneau , Alexei Baevski , Michael Auli

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-27 Qiu-Shi Zhu , Jie Zhang , Zi-Qiang Zhang , Li-Rong Dai

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the…

Machine Learning · Computer Science 2025-03-04 Jeffrey Gu , Serena Yeung-Levy

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…

Automatic speech recognition models require large amounts of speech recordings for training. However, the collection of such data often is cumbersome and leads to privacy concerns. Federated learning has been widely used as an effective…

Computation and Language · Computer Science 2024-05-28 Mohamed Nabih Ali , Alessio Brutti , Daniele Falavigna

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-16 Hejung Yang , Hong-Goo Kang