Related papers: IKFST: IOO and KOO Algorithms for Accelerated and …

End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and…

End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all…

Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words.…

This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Machine Translation group. The task consists of building a system capable of translating English audio recordings extracted from TED talks into…

The efficacy of Large Language Models (LLMs) in long-context tasks is often hampered by the substantial memory footprint and computational demands of the Key-Value (KV) cache. Current compression strategies, including token eviction and…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

By combining the undecimated wavelet transform within a Word Embedded Semantic Marginal Autoencoder (WESMA), this research study provides a novel strategy for improving security measures and denoising multiple languages. The incorporation…

It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech…

In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks. We propose a unified network that simultaneously localizes and recognizes text with a…

Collecting audio-text pairs is expensive; however, it is much easier to access text-only data. Unless using shallow fusion, end-to-end automatic speech recognition (ASR) models require architecture modifications or additional training…

The growing demand for high-quality point cloud transmission over wireless networks presents significant challenges, primarily due to the large data sizes and the need for efficient encoding techniques. In response to these challenges, we…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduces a positional mismatch, which leads to a dilemma between…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the…

Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algorithms, the recently proposed fully-connected tensor network…

Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years. Many end-to-end systems have been proposed and show advantages over conventional cascade systems, which are often composed of recognition, translation…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead,…

Language model approaches have recently been integrated into binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked…