Austria

Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which is naturally related to text. This paper surveys the integration of speech with LLMs, categorizing the methodologies into three primary approaches: text-based, latent-representation-based, and audio-token-based integration. We also demonstrate how these methods are applied across various speech-related applications and highlight the challenges in this field to offer inspiration for future research.

ACL 2025

When Large Language Models Meet Speech: A Survey on Integration Approaches

speech processing

survey

large language models

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

poster

This paper explores emotion-aware speech-to-text translation (ST) using generative error correction (GER) by large language models (LLMs). Despite recent advancements in ST, the impact of the emotional content has been overlooked. First, we enhance the translation of emotional speech by adopting the GER paradigm: Finetuned an LLM to generate the translation based on the decoded N-best hypotheses. Moreover, we combine the emotion and sentiment labels into the LLM finetuning process to enable the model to consider the emotion content. In addition, we project the ST model's latent representation into the LLM embedding space to further improve emotion recognition and translation. Experiments on an English-Chinese dataset show the effectiveness of the combination of GER, emotion and sentiment labels, and the projector for emotion-aware ST. We will release our codes to the public.

Generative Error Correction for Emotion-aware Speech-to-text Translation

Recent advancements in speech-to-speech dialogue systems leverage LLMs for multimodal interactions, yet they remain hindered by fine-tuning requirements, high computational overhead, and text-speech misalignment. Existing speech-enabled LLMs often degrade conversational quality by modifying the LLM, thereby compromising its linguistic capabilities. In contrast, we propose LLMVoX, a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming TTS system that generates high-quality speech with low latency, while fully preserving the capabilities of the base LLM. Our approach achieves a significantly lower Word Error Rate compared to speech-enabled LLMs, while operating at comparable latency. By decoupling speech synthesis from LLM processing via a multi-queue token streaming system, LLMVoX enables seamless, infinite-length dialogues. Its plug-and-play design also facilitates extension to various tasks with different backbones. Furthermore, LLMVoX generalizes to new languages with minimal dataset adaptation, attaining a low Character Error Rate on an Arabic speech task. Evaluations demonstrate that LLMVoX matches or surpasses existing speech-enabled LLMs in both speech quality and latency, while maintaining the original linguistic strengths of the LLM. Additionally, we have integrated LLMVoX with a Vision-Language Model to create an omni-model with speech, text, and vision capabilities, without requiring additional multimodal training.

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

Large Language Models (LLMs) have demonstrated remarkable performance across various Natural Language Processing (NLP) tasks, largely due to their generalisability and ability to perform tasks without additional training. However, their effectiveness for low-resource languages remains limited. In this study, we evaluate the performance of 47 publicly available LLMs on Maltese, a low-resource language, using a newly introduced benchmark covering 11 discriminative and generative tasks. Our experiments highlight that many models perform poorly, particularly on generative tasks, and that smaller fine-tuned models often perform better across all tasks. From our multidimensional analysis, we investigate various factors impacting performance. We conclude that prior exposure to Maltese during pre-training and instruction-tuning emerges as the most important factor. We also examine the trade-offs between fine-tuning and prompting, highlighting that while fine-tuning requires a higher initial cost, it yields better performance and lower inference costs. Through this work, we aim to highlight the need for more inclusive language technologies and recommend for researchers working with low-resource languages to consider more "traditional" language modelling approaches.

MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP

This paper presents elaborate results of experiments testing various encoder LLMs on their generalization capacities. We finetune 6 models with 5 seeds on 15 different datasplits, resulting in 450 finetuned models to compare on a challenging event detection task in Early Modern Dutch archival texts. Our experimental setup allows us to look at underresearched aspects of generalizability, namely i) shifts at multiple places in a modeling pipeline, ii) temporal and crosslingual shifts and iii) generalization over different initializations. We find that mBERT shows highest F1 performance, as well as stability over seeds and datasplits, contrary to XLM-R. We also find contemporary Dutch models do not generalize well to Early Modern Dutch as they underperform compared to crosslingual as well as historical models.

Temporal Generalizability in the Realm of Event Detection: The Role of Multilingual Models and Stochasticity

Dialogue Topic Segmentation (DTS) aims to divide dialogues into coherent segments. DTS plays a crucial role in various NLP downstream tasks, but suffers from chronic problems: data shortage, labeling ambiguity, and incremental complexity of recently proposed solutions. On the other hand, Despite advances in Large Language Models (LLMs) and reasoning strategies, these have rarely been applied to DTS. This paper introduces Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation, which utilizes LLM-based multi-step deductive reasoning to enhance DTS performance and enable case study using intermediate result. Our method employs a structured prompting approach for bidirectional context summarization, utterance intent classification, and deductive topic shift detection. In the intent classification process, we propose the generalizable intent list for domain-agnostic dialogue intent classification. Experiments in various dialogue settings demonstrate that Def-DTS consistently outperforms traditional and state-of-the-art approaches, with each subtask contributing to improved performance, particularly in reducing type 2 error. We also explore the potential for autolabeling, emphasizing the importance of LLM reasoning techniques in DTS.

Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation

Key Information Extraction (KIE) from visually rich documents is commonly approached as either fine-grained token classification or coarse-grained entity extraction. While token-level models capture spatial and visual cues, entity-level models better represent logical dependencies and align with real-world use cases.
We introduce PM3-KIE, a probabilistic multi-task meta-model that incorporates both fine-grained and coarse-grained models. It serves as a lightweight reasoning layer that jointly predicts entities and all appearances in a document. PM3-KIE incorporates domain-specific schema constraints to enforce logical consistency and integrates large language models for semantic validation, thereby reducing extraction errors.
Experiments on two public datasets, DeepForm and FARA, show that PM3-KIE outperforms three state-of-the-art models and a stacked ensemble, achieving a statistically significant 2% improvement in F1 score.

PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction

The exponential growth of offensive language on social media tends to fuel online harassment and challenges detection mechanisms. Hate speech detection is commonly treated as a monolingual or multilingual sentence-level classification task. However, profane language tends to contain code-mixing, a combination of more than one language, which requires a more nuanced detection approach than binary classification. A general lack of available code-mixed datasets aggravates the problem. To address this issue, we propose five word-level annotated hate speech datasets, EN and DE from social networks, one subset of the DE-EN Offensive Content Detection Code-Switched Dataset, one DE-EN code-mixed German rap lyrics held-out test set, and a cross-domain held-out test set. We investigate the capacity of fine-tuned German-only, German-English bilingual, and German-English code-mixed token classification XLM-R models to generalize to code-mixed hate speech in German rap lyrics in zero-shot domain transfer as well as across different domains. The results show that bilingual fine-tuning facilitates not only the detection of code-mixed hate speech but also neologisms, addressing the inherent dynamics of profane language use.

Word-Level Detection of Code-Mixed Hate Speech with Multilingual Domain Transfer

Compositionality is a key aspect of human intelligence, essential for reasoning and generalization. While transformer-based models have become the de facto standard for many language modeling tasks, little is known about how they represent compound words, and whether these representations are compositional. In this study, we test compositionality in Mistral, OpenAI Large, and Google embedding models, and compare them with BERT. First, we evaluate compositionality in the representations by examining six diverse models of compositionality (addition, multiplication, dilation, regression, etc.). We find that ridge regression, albeit linear, best accounts for compositionality. Surprisingly, we find that the classic vector addition model performs almost as well as any other model. Next, we verify that most embedding models are highly compositional, while BERT shows much poorer compositionality. We verify and visualize our findings with a synthetic dataset consisting of fully transparent adjective-noun compositions. Overall, we present a thorough investigation of compositionality.

How do Transformer Embeddings Represent Compositions? A Functional Analysis

The retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Recently, retrievers have been introduced in knowledge-grounded dialog systems to improve knowledge acquisition. In knowledge-grounded dialog systems, when conditioning on a given context, there may be multiple relevant and correlated knowledge pieces. However, knowledge pieces are usually assumed to be conditionally independent in current retriever models. To address this issue, we propose Entriever, an energy-based retriever. The Entriever directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately, with the relevance score defined by an energy function. We explore various architectures of energy functions and different training methods for Entriever, and show that Entriever substantially outperforms the strong cross-encoder baseline in knowledge retrieval tasks. Furthermore, we show that in semi-supervised training of knowledge-grounded dialog systems, Entriever enables the effective scoring of retrieved knowledge pieces and leads to a significant improvement in the end-to-end performance of the dialog system.

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems

Discourse particles are crucial elements that subtly shape the meaning of text. These words, often polyfunctional, give rise to nuanced and often quite disparate semantic/discourse effects,
as exemplified by the diverse uses of the particle *just* (e.g., exclusive, temporal, emphatic). 
This work investigates the capacity of LLMs to distinguish the fine-grained senses of English *just*, a well-studied example in formal semantics, using data meticulously created and labeled by expert linguists. Our findings reveal that while LLMs exhibit some ability to differentiate between broader categories, they struggle to fully capture more subtle nuances, highlighting a gap in their understanding of discourse particles.

Downloads

Next from ACL 2025

Generative Error Correction for Emotion-aware Speech-to-text Translation

Similar lecture

Recent Advances in Speech Language Models: A Survey

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES