English
Related papers

Related papers: Qwen vs. Gemma Integration with Whisper: A Compara…

200 papers

In this work, we present and evaluate SELMA, a Speech-Enabled Language Model for virtual Assistant interactions that integrates audio and text as inputs to a Large Language Model (LLM). SELMA is designed to handle three primary and two…

Sound · Computer Science 2025-02-04 Dominik Wagner , Alexander Churchill , Siddharth Sigtia , Erik Marchi

Recently, large-scale pre-trained speech encoders and Large Language Models (LLMs) have been released, which show state-of-the-art performance on a range of spoken language processing tasks including Automatic Speech Recognition (ASR). To…

Computation and Language · Computer Science 2025-05-19 Rao Ma , Tongzhou Chen , Kartik Audhkhasi , Bhuvana Ramabhadran

Large language models (LLMs) are increasingly applied in computer science education for tasks such as tutoring, content generation, and code assessment. However, systematic evaluations aligned with formal curricula and certification…

In this paper, we explore several new schemes to train a seq2seq model to integrate a pre-trained LM. Our proposed fusion methods focus on the memory cell state and the hidden state in the seq2seq decoder long short-term memory (LSTM), and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-05 Jaejin Cho , Shinji Watanabe , Takaaki Hori , Murali Karthick Baskar , Hirofumi Inaguma , Jesus Villalba , Najim Dehak

In this work, we study how to best utilize pre-trained LLMs for automatic speech recognition. Specifically, we compare the tight integration of an acoustic model (AM) with the LLM ("speech LLM") to the traditional way of combining AM and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-17 Robin Schmitt , Albert Zeyer , Mohammad Zeineldeen , Ralf Schlüter , Hermann Ney

Complex Word Identification (CWI) is an essential step in the lexical simplification task and has recently become a task on its own. Some variations of this binary classification task have emerged, such as lexical complexity prediction…

Computation and Language · Computer Science 2024-11-05 Răzvan-Alexandru Smădu , David-Gabriel Ion , Dumitru-Clementin Cercel , Florin Pop , Mihaela-Claudia Cercel

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…

Non-intrusive speech quality assessment (SQA) systems suffer from limited training data and costly human annotations, hindering their generalization to real-time conferencing calls. In this work, we propose leveraging large language models…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-11 Fredrik Cumlin , Xinyu Liang , Anubhab Ghosh , Saikat Chatterjee

Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often…

Computation and Language · Computer Science 2025-08-14 Shikhar Srivastava , Md Yousuf Harun , Robik Shrestha , Christopher Kanan

Long-form speech recognition with large encoder-decoder models such as Whisper often exhibit hallucinations, repetition loops, and content omissions. These errors can accumulate and be further amplified when the previous segment's…

Sound · Computer Science 2026-03-09 Hoseong Ahn , Jeongyun Chae , Yoonji Park , Kyuhong Shim

Conversational automatic speech recognition remains challenging due to overlapping speech, far-field noise, and varying speaker counts. While recent LLM-based systems perform well on single-speaker benchmarks, their robustness in…

Computation and Language · Computer Science 2026-03-25 Naohiro Tawara , Samuele Cornell , Alexander Polok , Marc Delcroix , Lukáš Burget , Shinji Watanabe

We introduce FuseChat-3.0, a suite of large language models (LLMs) developed by integrating the strengths of heterogeneous source LLMs into more compact target LLMs. Our source models include the powerful Gemma-2-27B-it,…

Computation and Language · Computer Science 2025-03-07 Ziyi Yang , Fanqi Wan , Longguang Zhong , Canbin Huang , Guosheng Liang , Xiaojun Quan

Whisper has become the de-facto encoder for extracting general-purpose audio features in large audio-language models, where a 30-second clip is typically represented by 1500 frame features projected into an LLM. In contrast, audio-text…

Sound · Computer Science 2026-01-23 Gokul Karthik Kumar , Ludovick Lepauloux , Hakim Hacid

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech…

Computation and Language · Computer Science 2025-02-12 Rao Ma , Mengjie Qian , Yassir Fathullah , Siyuan Tang , Mark Gales , Kate Knill

Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work…

Computation and Language · Computer Science 2024-01-02 Hongkun Hao , Long Zhou , Shujie Liu , Jinyu Li , Shujie Hu , Rui Wang , Furu Wei

Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding…

Computation and Language · Computer Science 2024-07-11 Frank Palma Gomez , Ramon Sanabria , Yun-hsuan Sung , Daniel Cer , Siddharth Dalmia , Gustavo Hernandez Abrego

Large language models excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing encoder-plus-decoder methods such as LangBridge and MindMerger raise accuracy on mid and high-resource…

Computation and Language · Computer Science 2026-03-09 Kosei Uemura , David Guzmán , Quang Phuoc Nguyen , Jesujoba Oluwadara Alabi , En-shiun Annie Lee , David Ifeoluwa Adelani

The rapid spread of multilingual misinformation requires robust automated fact verification systems capable of handling fine-grained veracity assessments across diverse languages. While large language models have shown remarkable…

Computation and Language · Computer Science 2025-07-29 Hanna Shcharbakova , Tatiana Anikina , Natalia Skachkova , Josef van Genabith

Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility…

Computation and Language · Computer Science 2025-11-18 Minghan Wang , Jinming Zhao , Thuy-Trang Vu , Fatemeh Shiri , Ehsan Shareghi , Gholamreza Haffari
‹ Prev 1 3 4 5 6 7 10 Next ›