Related papers: Wavelet Scattering Transform for Improving General…

In recent years, End-to-End speech recognition technology based on deep learning has developed rapidly. Due to the lack of Turkish speech data, the performance of Turkish speech recognition system is poor. Firstly, this paper studies a…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Stuttering is a neuro-developmental speech impairment characterized by uncontrolled utterances (interjections) and core behaviors (blocks, repetitions, and prolongations), and is caused by the failure of speech sensorimotors. Due to its…

Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic…

Spoken language change detection (LCD) refers to detecting language switching points in a multilingual speech signal. Speaker change detection (SCD) refers to locating the speaker change points in a multispeaker speech signal. The objective…

This paper proposes joint speaker feature learning methods for zero-shot adaptation of audio-visual multichannel speech separation and recognition systems. xVector and ECAPA-TDNN speaker encoders are connected using purpose-built fusion…

The performance of Large Language Models (LLMs) on natural language tasks can be improved through both supervised fine-tuning (SFT) and in-context learning (ICL), which operate via distinct mechanisms. Supervised fine-tuning updates the…

The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on…

Informal transliteration from other languages to English is prevalent in social media threads, instant messaging, and discussion forums. Without identifying the language of such transliterated text, users who do not speak that language…

Facing the diversity and growth of the musical field nowadays, the search for precise songs becomes more and more complex. The identity of the singer facilitates this search. In this project, we focus on the problem of identifying the…

IRSTD (InfraRed Small Target Detection) detects small targets in infrared blurry backgrounds and is essential for various applications. The detection task is challenging due to the small size of the targets and their sparse distribution in…

Diffusion models have emerged as potential tools to tackle the challenge of sparse-view CT reconstruction, displaying superior performance compared to conventional methods. Nevertheless, these prevailing diffusion models predominantly focus…

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has emerged as the standard post-training paradigm for large language models (LLMs). However, the conventional SFT process, driven by Cross-Entropy (CE) loss, often…

We present MaskLID, a simple, yet effective, code-switching (CS) language identification (LID) method. MaskLID does not require any training and is designed to complement current high-performance sentence-level LIDs. Sentence-level LIDs are…

Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared…

Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to…

Flattery is an important aspect of human communication that facilitates social bonding, shapes perceptions, and influences behavior through strategic compliments and praise, leveraging the power of speech to build rapport effectively. Its…

Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time spectrum of a signal. However, the duration of short STFT…

Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields…

Named Entity Recognition (NER) models trained on clean, high-resource corpora exhibit catastrophic performance collapse when deployed on noisy, sparse User-Generated Content (UGC), such as social media. Prior research has predominantly…