Related papers: STRATA: Word Boundaries & Phoneme Recognition From…

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…

Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements…

In schema-guided dialogue state tracking models estimate the current state of a conversation using natural language descriptions of the service schema for generalization to unseen services. Prior generative approaches which decode slot…

With the advent of Deep Learning based Artificial Neural Networks models, Natural Language Processing (NLP) has witnessed significant improvements in textual data processing in terms of its efficiency and accuracy. However, the research is…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Urdu is a cursive script language and has similarities with Arabic and many other South Asian languages. Urdu is difficult to classify due to its complex geometrical and morphological structure. Character classification can be processed…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Mispronunciation detection and diagnosis (MDD) technology is a key component of computer-assisted pronunciation training system (CAPT). In the field of assessing the pronunciation quality of constrained speech, the given transcriptions can…

In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian Consonant-Vowel Combination (PCVC) speech dataset. Nowadays, deep neural networks play a crucial role in classification tasks. However, the…

Speech transcription, emotion recognition, and language identification are usually considered to be three different tasks. Each one requires a different model with a different architecture and training process. We propose using a recurrent…

Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized…

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. However, if the available unlabeled speech is mismatched to…

Training speech recognition systems on noisy transcripts is a significant challenge in industrial pipelines, where datasets are enormous and ensuring accurate transcription for every instance is difficult. In this work, we introduce novel…

Sequence expansion between encoder and decoder is a critical challenge in sequence-to-sequence TTS. Attention-based methods achieve great naturalness but suffer from unstable issues like missing and repeating phonemes, not to mention…

Self-attention scales quadratically with sequence length, limiting transformer-based speech models on edge devices. We introduce the Learnable Pulse Accumulator (LPA), an O(n) replacement that substitutes key-query dot products with learned…

Although many Automatic Speech Recognition (ASR) systems have been developed for Modern Standard Arabic (MSA) and Dialectal Arabic (DA), few studies have focused on dialect-specific implementations, particularly for low-resource Arabic…

Understanding the intention of the users and recognizing the semantic entities from their sentences, aka natural language understanding (NLU), is the upstream task of many natural language processing tasks. One of the main challenges is to…

Named Entity Recognition (NER), a fundamental task in Natural Language Processing (NLP), has shown significant advancements for high-resource languages. However, due to a lack of annotated datasets and limited representation in Pre-trained…

Large Audio-Language Models (LALMs) often suffer from audio-textual attention imbalance, prioritizing text over acoustic information, particularly in the multi-modal fusion layers of the Transformer architecture. This bias hinders their…