Related papers: SALSA: Speedy ASR-LLM Synchronous Aggregation

Automatic speech recognition (ASR) systems normally consist of an acoustic model (AM) and a language model (LM). The acoustic model estimates the probability distribution of text given the input speech, while the language model calibrates…

Advances in self-supervised encoders have improved Visual Speech Recognition (VSR). Recent approaches integrating these encoders with LLM decoders improves transcription accuracy; however, it remains unclear whether these gains stem from…

This paper presents Seewo's systems for both tracks of the Multilingual Conversational Speech Language Model Challenge (MLC-SLM), addressing automatic speech recognition (ASR) and speaker diarization with ASR (SD-ASR). We introduce a…

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…

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…

Parallel cross-lingual summarization data is scarce, requiring models to better use the limited available cross-lingual resources. Existing methods to do so often adopt sequence-to-sequence networks with multi-task frameworks. Such…

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

Despite remarkable achievements, automatic speech recognition (ASR) in low-resource scenarios still faces two challenges: high-quality data scarcity and high computational demands. This paper proposes EThai-ASR, the first to apply large…

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

We propose a new shallow fusion (SF) method to exploit an external backward language model (BLM) for end-to-end automatic speech recognition (ASR). The BLM has complementary characteristics with a forward language model (FLM), and the…

Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that,…

Automatic Speech Recognition (ASR) is a key element in new services that helps users to interact with an automated system. Deep learning methods have made it possible to deploy systems with word error rates below 5% for ASR of English.…

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large…

Automatic Speech Recognition (ASR) systems remain prone to errors that affect downstream applications. In this paper, we propose LIR-ASR, a heuristic optimized iterative correction framework using LLMs, inspired by human auditory…

Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic)…

This paper introduces three self-contained data augmentation methods for low-resource Automatic Speech Recognition (ASR). Our techniques first generate novel text--using gloss-based replacement, random replacement, or an LLM-based…

Stochastic Alternating Least Squares (SALS) is a method that approximates the canonical decomposition of averages of sampled random tensors. Its simplicity and efficient memory usage make SALS an ideal tool for decomposing tensors in an…

The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated…

In this paper, we consider the channel estimation problem in sub-6 GHz uplink wideband MIMO-OFDM communication systems, where a user equipment with a fully-digital beamforming structure is communicating with a base station having a hybrid…