Related papers: Learning Intonation Pattern Embeddings for Arabic …

We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both…

The Arabic language is characterized by a rich tapestry of regional dialects that differ substantially in phonetics and lexicon, reflecting the geographic and cultural diversity of its speakers. Despite the availability of many…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling,…

End-to-end deep learning language or dialect identification systems operate on the spectrogram or other acoustic feature and directly generate identification scores for each class. An important issue for end-to-end systems is to have some…

Developing Automatic Speech Recognition (ASR) systems for Tunisian Arabic Dialect is challenging due to the dialect's linguistic complexity and the scarcity of annotated speech datasets. To address these challenges, we propose the LinTO…

The phonological discrepancies between a speaker's native (L1) and the non-native language (L2) serves as a major factor for mispronunciation. This paper introduces a novel multilingual MDD architecture, L1-MultiMDD, enriched with L1-aware…

Transcribed speech and user-generated text in Arabic typically contain a mixture of Modern Standard Arabic (MSA), the standardized language taught in schools, and Dialectal Arabic (DA), used in daily communications. To handle this…

We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text.…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introducing seven synthetic datasets in dialects alongside Modern…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…

Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding…

Arabic dialect identification is a complex problem for a number of inherent properties of the language itself. In this paper, we present the experiments conducted, and the models developed by our competing team, Mawdoo3 AI, along the way to…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for…

Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone…