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, their effectiveness in real-world multilingual conversations remains limited by the scarcity of data that captures natural conversational phenomena. To address this, the MLC-SLM Challenge provides a multilingual conversational dataset and evaluates models on two tasks: ASR with oracle segmentation (Task I) and joint diarization and recognition without oracle information (Task II). In this paper, we focus on Task II and propose a unified speech LLM that jointly performs diarization and ASR in an end-to-end manner. By reformulating the training data format and modifying the inference procedure, our model addresses the ambiguity inherent in pre-segmented audio and achieves a 54.87\% relative improvement in tcpWER/tcpCER over the baseline, ranking 8th overall, despite using a smaller LLM backbone. We also report results from Task I using a fine-tuned speech LLM.

Speech Emotion Recognition (SER) has seen significant progress with deep learning, yet remains challenging for Low-Resource Languages (LRLs) due to the scarcity of annotated data. In this work, we explore unsupervised learning to improve SER in low-resource settings. Specifically, we investigate contrastive learning (CL) and Bootstrap Y our Own Latent (BYOL) as self-supervised approaches to enhance cross-lingual generalization. Our methods achieve notable F1 score improvements of 10.6% in Urdu, 15.2% in German, and 13.9% in Bangla, demonstrating their effectiveness in LRLs. Additionally, we analyze model behavior to provide insights on key factors influencing performance across languages, and also highlighting challenges in low-resource SER. This work provides a foundation for developing more inclusive, explainable, and robust emotion recognition systems for underrepresented languages.

A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based method that takes speaker embeddings extracted from a pre-trained speaker recognition model and generates refined embeddings. For training, our approach progressively adds Gaussian noise to both clean and noisy speaker embeddings extracted from clean and noisy speech, respectively, via forward process of a diffusion model, and then reconstructs them to clean embeddings in the reverse process. While inferencing, all embeddings are regenerated via diffusion process. Our method needs neither speaker label nor any modification to the existing speaker recognition pipeline. Experiments on evaluation sets simulating environment mismatch scenarios show that our method can improve recognition accuracy by up to 19.6% over baseline models while retaining performance on conventional scenarios. We publish our code here https://github.com/kaistmm/seed-pytorch

In qualitative research, data transcription is often labor-intensive and time-consuming. To expedite this process, a workflow utilizing artificial intelligence (AI) was developed. This workflow not only enhances transcription speed but also addresses the issue of AI-generated transcripts often lacking compatibility with standard content analysis software. Within this workflow, automatic speech recognition is employed to create initial transcripts from audio recordings, which are then formatted to be compatible with content analysis software such as ATLAS.ti or MAXQDA. Empirical data from a study of 12 interviews suggests that this workflow can reduce transcription time by up to 46.2%. Furthermore, by using widely used standard software, this process is suitable for both students and researchers while also being adaptable to a variety of learning, teaching, and research environments. It is also particularly beneficial for non-native speakers. In addition, the workflow is GDPR-compliant and facilitates local, offline transcript generation, which is crucial when dealing with sensitive data.

However, human auditory perception is inherently selective: listeners focus on specific speakers while ignoring others in complex auditory scenes. Existing models do not incorporate this selectivity, limiting their ability to generate perceptionaligned responses. To address this, we introduce Intention-Informed Auditory Scene Understanding (II-ASU) and present Auditory Attention-Driven LLM (AAD-LLM), a prototype system that integrates brain signals to infer listener attention. AAD-LLM extends an auditory LLM by incorporating intracranial electroencephalography (iEEG) recordings to decode which speaker a listener is attending to and refine responses accordingly. The model first predicts the attended speaker from neural activity, then conditions response generation on this inferred attentional state. We evaluate AAD-LLM on speaker description, speech transcription and extraction, and question answering Figure 1: AAD-LLM is a brain-computer interface in multitalker scenarios, with both objective (BCI) for auditory scene understanding. It decodes neural and subjective ratings showing improved alignment signals to identify the attended speaker and integrates with listener intention. By taking a first this information into a language model, generating responses step toward intention-aware auditory AI, this that align with the listener's perceptual focus.

The aim of this paper is to investigate the benefit of combining both language and acoustic modelling for speaker diarization. Although conventional systems only use acoustic features, in some scenarios linguistic data contain high discriminative speaker information, even more reliable than the acoustic ones. In this study we analyze how an appropriate fusion of both kind of features is able to obtain good results in these cases. The proposed system is based on an iterative algorithm where a LSTM network is used as a speaker classifier. The network is fed with character-level word embeddings and a GMM based acoustic score created with the output labels from previous iterations. The presented algorithm has been evaluated in a Call-Center database, which is composed of telephone interview audios. The combination of acoustic features and linguistic content shows a 84.29% improvement in terms of a word-level DER as compared to a HMM/VB baseline system. The results of this study confirms that linguistic content can be efficiently used for some speaker recognition tasks.

Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker transitions and overlapping speech. Recently, language models including fine-tuned large language models (LLMs) have shown to be effective as a second-pass speaker error corrector by leveraging lexical context in the transcribed output. In this work, we introduce a novel acoustic conditioning approach to provide more fine-grained information from the acoustic diarizer to the LLM. We also show that a simpler constrained decoding strategy reduces LLM hallucinations, while avoiding complicated post-processing. Our approach significantly reduces the speaker error rates by 24-43% across Fisher, Callhome, and RT03-CTS datasets, compared to the first-pass Acoustic SD.

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning of joint modules, limiting their adaptability and general efficiency. This paper introduces a novel approach, leveraging a frozen multilingual ASR model to incorporate speaker attribution into the transcriptions, using only standard monolingual ASR datasets. Our method involves training a speaker module to predict speaker embeddings based on weak labels without requiring additional ASR model modifications. Despite being trained exclusively with non-overlapping monolingual data, our approach effectively extracts speaker attributes across diverse multilingual datasets, including those with overlapping speech. Experimental results demonstrate competitive performance compared to strong baselines, highlighting the model's robustness and potential for practical applications.

Television is often seen as a site for subcultural identification and subversive fantasy, including in queer cultures. How might we measure subversion, or the degree to which the depiction of social relationship between a dyad (e.g. two characters who are colleagues) deviates from its typical representation on TV? To explore this question, we introduce the task of stereotypic relationship extraction. Built on cognitive stylistics, linguistic anthropology, and dialogue relation extraction, in this paper, we attempt to model the cognitive process of stereotyping TV characters in dialogic interactions. Given a dyad, we want to predict: what social relationship do the speakers exhibit through their words? Subversion is then characterized by the discrepancy between the distribution of the model's predictions and the ground truth labels. To demonstrate the usefulness of this task and gesture at a methodological intervention, we enclose four case studies to characterize the representation of queer relationalities in the Big Bang Theory, Frasier, and Gilmore Girls, as we explore the suspicious and reparative modes of reading with our computational methods.

Speech applications dealing with conversations require not only recognizing the spoken words but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems, namely, an automatic speech recognition (ASR) system and a speaker diarization (SD) system. In practical settings, speaker diarization systems can experience significant degradation in performance due to a variety of factors, including uniform segmentation with a high temporal resolution, inaccurate word timestamps, incorrect clustering and estimation of speaker numbers, as well as background noise. Therefore, it is important to automatically detect errors and make corrections if possible. We used a second-pass speaker tagging correction system based on a non-autoregressive language model to correct mistakes in words placed at the borders of sentences spoken by different speakers. We first show that the employed error correction approach leads to reductions in word diarization error rate (WDER) on two datasets: TAL and test set of Fisher. Additionally, we evaluated our system in the Post-ASR Speaker Tagging Correction challenge and observed significant improvements in cpWER compared to baseline methods.