English
Related papers

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

200 papers

Combining different models is a widely used paradigm in machine learning applications. While the most common approach is to form an ensemble of models and average their individual predictions, this approach is often rendered infeasible by…

Machine Learning · Computer Science 2023-05-17 Sidak Pal Singh , Martin Jaggi

Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…

Computation and Language · Computer Science 2023-06-22 Simon Berger , Peter Vieting , Christoph Boeddeker , Ralf Schlüter , Reinhold Haeb-Umbach

Speech Large Language Models (Speech LLMs) have emerged as a crucial paradigm in recent years, extending the capabilities of traditional LLMs to speech tasks such as automatic speech recognition (ASR) and spoken dialogue modeling. However,…

Computation and Language · Computer Science 2025-07-08 Phurich Saengthong , Boonnithi Jiaramaneepinit , Sheng Li , Manabu Okumura , Takahiro Shinozaki

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Artificial Intelligence · Computer Science 2025-03-28 Jiaqi Han , Jingwen Ye , Shunyu Liu , Haofei Zhang , Jie Song , Zunlei Feng , Mingli Song

Cross-lingual speech emotion recognition (SER) is important for a wide range of everyday applications. While recent SER research relies heavily on large pretrained models for emotion training, existing studies often concentrate solely on…

Sound · Computer Science 2024-07-09 Shreya G. Upadhyay , Carlos Busso , Chi-Chun Lee

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific…

Audio and Speech Processing · Electrical Eng. & Systems 2018-12-24 Jang-Hyun Kim , Jaejun Yoo , Sanghyuk Chun , Adrian Kim , Jung-Woo Ha

While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-24 Runyan Yang , Yuke Si , Yingying Gao , Junlan Feng , Chao Deng , Shilei Zhang

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-11 Chunyu Sun , Bingyu Liu , Zhichao Cui , Junhan Shi , Anbin Qi , Tian-hao Zhang , Dinghao Zhou , Lewei Lu

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

Computation and Language · Computer Science 2019-12-17 Yuchen Liu , Jiajun Zhang , Hao Xiong , Long Zhou , Zhongjun He , Hua Wu , Haifeng Wang , Chengqing Zong

Transformers have evolved with great success in various artificial intelligence tasks. Thanks to our recent prevalence of self-attention mechanisms, which capture long-term dependency, phenomenal outcomes in speech processing and…

Computation and Language · Computer Science 2024-08-28 Shruti Singh , Muskaan Singh , Virender Kadyan

While training large language models (LLMs) from scratch can generate models with distinct functionalities and strengths, it comes at significant costs and may result in redundant capabilities. Alternatively, a cost-effective and compelling…

Computation and Language · Computer Science 2024-01-23 Fanqi Wan , Xinting Huang , Deng Cai , Xiaojun Quan , Wei Bi , Shuming Shi

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…

Computation and Language · Computer Science 2020-10-28 Suyoun Kim , Yuan Shangguan , Jay Mahadeokar , Antoine Bruguier , Christian Fuegen , Michael L. Seltzer , Duc Le

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Desh Raj

Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performance. However, the integration of multi-layer visual features…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Junyan Lin , Haoran Chen , Yue Fan , Yingqi Fan , Xin Jin , Hui Su , Jinlan Fu , Xiaoyu Shen

Diffusion-based generative speech enhancement (SE) has recently received attention, but reverse diffusion remains time-consuming. One solution is to initialize the reverse diffusion process with enhanced features estimated by a predictive…

The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understanding and generation. While existing LSLMs often concentrate…

Computation and Language · Computer Science 2025-11-03 Shoutao Guo , Shaolei Zhang , Qingkai Fang , Zhengrui Ma , Min Zhang , Yang Feng

Integrating Federated Learning (FL) with self-supervised learning (SSL) enables privacy-preserving fine-tuning for speech tasks. However, federated environments exhibit significant heterogeneity: clients differ in computational capacity,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-26 Xin Guo , Chunrui Zhao , Hong Jia , Ting Dang , Gongping Huang , Xianrui Zheng , Yan Gao

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Computation and Language · Computer Science 2026-03-31 Mingyang Song , Mao Zheng

The local and global features are both essential for automatic speech recognition (ASR). Many recent methods have verified that simply combining local and global features can further promote ASR performance. However, these methods pay less…

Computation and Language · Computer Science 2023-05-30 Zhi-Hao Lai , Tian-Hao Zhang , Qi Liu , Xinyuan Qian , Li-Fang Wei , Song-Lu Chen , Feng Chen , Xu-Cheng Yin

Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-22 Bunlong Lay , Rostislav Makarov , Simon Welker , Maris Hillemann , Timo Gerkmann