Related papers: TICL+: A Case Study On Speech In-Context Learning …

In the last decades, scene text recognition has gained worldwide attention from both the academic community and actual users due to its importance in a wide range of applications. Despite achievements in optical character recognition, scene…

Numerous noise adaptation techniques have been proposed to fine-tune deep-learning models in speech enhancement (SE) for mismatched noise environments. Nevertheless, adaptation to a new environment may lead to catastrophic forgetting of the…

Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic transcriptions. However, obtaining reliably high-quality ASR transcriptions for child…

Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the…

Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion…

End-to-end (E2E) models have achieved promising results on multiple speech recognition benchmarks, and shown the potential to become the mainstream. However, the unified structure and the E2E training hamper injecting contextual information…

Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt, eliminating the need for parameter updates and achieving competitive performance. In this paper, we…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models' ability to extract critical details from approximately…

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns…

Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates. However, many studies…

This paper describes the SPAPL system for the INTERSPEECH 2021 Challenge: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech in German. ~ 5 hours of transcribed data and ~ 60 hours of untranscribed data are…

This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level…

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot…

Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic…

We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of…

This paper presents the "Ethiopian" system for the SLT 2021 Children Speech Recognition Challenge. Various data processing and augmentation techniques are proposed to tackle children's speech recognition problem, especially the lack of the…

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit…

There has been significant recent interest in understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform…

Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations. In this paper, we propose a novel Inherent Consistent Learning (ICL) method, aims to learn robust…