English
Related papers

Related papers: SALSA: Speedy ASR-LLM Synchronous Aggregation

200 papers

End-to-end (E2E) automatic speech recognition (ASR) systems have revolutionized the field by integrating all components into a single neural network, with attention-based encoder-decoder models achieving state-of-the-art performance.…

Computation and Language · Computer Science 2025-07-01 Duygu Altinok

Large language models (LLMs) have demonstrated remarkable advancements in language understanding and generation. Building on the success of text-based LLMs, recent research has adapted these models to use speech embeddings for prompting,…

Computation and Language · Computer Science 2025-03-28 Ke Hu , Zhehuai Chen , Chao-Han Huck Yang , Piotr Żelasko , Oleksii Hrinchuk , Vitaly Lavrukhin , Jagadeesh Balam , Boris Ginsburg

Vision-language models (VLMs) excel in tasks such as visual question answering and image captioning. However, VLMs are often limited by their use of pretrained image encoders, like CLIP, leading to image understanding errors that hinder…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Aristeidis Panos , Rahaf Aljundi , Daniel Olmeda Reino , Richard E. Turner

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context…

Sound · Computer Science 2026-01-19 Bingshen Mu , Hexin Liu , Hongfei Xue , Kun Wei , Lei Xie

Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…

Computation and Language · Computer Science 2021-03-26 Tong Cui , Jinghui Xiao , Liangyou Li , Xin Jiang , Qun Liu

This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus sampling, often struggle…

Computation and Language · Computer Science 2025-06-12 Jaydip Sen , Saptarshi Sengupta , Subhasis Dasgupta

We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium-resource scenarios. Through extensive experiments, we show…

Large language models (LLMs) provide strong semantic priors that can improve multi-talker automatic speech recognition (MT-ASR), but using an LLM as an autoregressive decoder is computationally expensive and remains fragile under heavy…

Sound · Computer Science 2026-03-12 Hao Shi , Yusuke Fujita , Roman Koshkin , Mengjie Zhao , Yuan Gao , Lianbo Liu , Yui Sudo

Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…

Sound · Computer Science 2026-01-30 Manali Sharma , Riya Naik , Buvaneshwari G

While LLM-based Automatic Speech Recognition (ASR) achieves high accuracy, its speed is limited by sequential autoregressive decoding. Diffusion Language Models (DLMs) offer a parallel alternative, yet their decoding strategies remain…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-29 Jeong Hun Yeo , Minsu Kim , Hyeongseop Rha , Yong Man Ro

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-06 Matthew Wiesner , Adithya Renduchintala , Shinji Watanabe , Chunxi Liu , Najim Dehak , Sanjeev Khudanpur

Modern automatic speech recognition (ASR) models, such as OpenAI's Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce…

Machine Learning · Computer Science 2025-08-26 Keisuke Kamahori , Jungo Kasai , Noriyuki Kojima , Baris Kasikci

Adapting pre-trained text Large Language Models (LLMs) into Speech Language Models (Speech LMs) via continual pretraining on speech data is promising, but often degrades the original text capabilities. We propose Multimodal Depth Upscaling,…

Computation and Language · Computer Science 2026-04-02 Kazuki Yano , Jun Suzuki , Shinji Watanabe

The end-to-end ASR model is often desired in the streaming multilingual scenario since it is easier to deploy and can benefit from pre-trained speech models such as powerful foundation models. Meanwhile, the heterogeneous nature and…

Computation and Language · Computer Science 2024-01-18 Junwen Bai , Bo Li , Qiujia Li , Tara N. Sainath , Trevor Strohman

Large language models (LLMs) excel at mathematical reasoning and logical problem-solving. The current popular training paradigms primarily use supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance the models' reasoning…

Machine Learning · Computer Science 2025-08-05 Jack Chen , Fazhong Liu , Naruto Liu , Yuhan Luo , Erqu Qin , Harry Zheng , Tian Dong , Haojin Zhu , Yan Meng , Xiao Wang

Contextual ASR or hotword customization holds substantial practical value. Despite the impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) systems, they often face challenges in accurately recognizing rare…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-12 Guanrou Yang , Ziyang Ma , Zhifu Gao , Shiliang Zhang , Xie Chen

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Computation and Language · Computer Science 2024-12-24 Keqi Deng , Jinxi Guo , Yingyi Ma , Niko Moritz , Philip C. Woodland , Ozlem Kalinli , Mike Seltzer

Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-23 Sujith Pulikodan , Sahapthan K , Prasanta Kumar Ghosh , Visruth Sanka , Nihar Desai

Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-27 Chia-Yu Lee , Huang-Cheng Chou , Tzu-Quan Lin , Yuanchao Li , Ya-Tse Wu , Shrikanth Narayanan , Chi-Chun Lee

Despite the widespread availability of LLMs, there remains a substantial gap in their capabilities and availability across diverse languages. One approach to address these issues has been to take an existing pre-trained LLM and continue to…

Computation and Language · Computer Science 2024-07-19 Zoltan Csaki , Bo Li , Jonathan Li , Qiantong Xu , Pian Pawakapan , Leon Zhang , Yun Du , Hengyu Zhao , Changran Hu , Urmish Thakker