相关论文: Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning…

The ability to model and automatically detect dialogue act is an important step toward understanding spontaneous speech and Instant Messages. However, it has been difficult to infer a dialogue act from a surface utterance because it highly…

A reasonable amount of annotated data is required for fine-tuning pre-trained language models (PLM) on downstream tasks. However, obtaining labeled examples for different language varieties can be costly. In this paper, we investigate the…

Arabic is a complex language with many varieties and dialects spoken by over 450 millions all around the world. Due to the linguistic diversity and variations, it is challenging to build a robust and generalized ASR system for Arabic. In…

Hausa texts are often characterized by writing anomalies, such as incorrect character substitutions and spacing errors, which sometimes hinder natural language processing (NLP) applications. This paper presents an approach to automatically…

We propose two improvements to target-speaker voice activity detection (TS-VAD), the core component in our proposed speaker diarization system that was submitted to the 2022 Multi-Channel Multi-Party Meeting Transcription (M2MeT) challenge.…

Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first…

We present ARETA, an automatic error type annotation system for Modern Standard Arabic. We design ARETA to address Arabic's morphological richness and orthographic ambiguity. We base our error taxonomy on the Arabic Learner Corpus (ALC)…

This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic…

This paper presents a comprehensive examination of the impact of tokenization strategies and vocabulary sizes on the performance of Arabic language models in downstream natural language processing tasks. Our investigation focused on the…

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…

The developments in transformer encoder-decoder architectures have led to significant breakthroughs in machine translation, Automatic Speech Recognition (ASR), and instruction-based chat machines, among other applications. The pre-trained…

Based on an annotated multimedia corpus, television series Mar{\=a}y{\=a} 2013, we dig into the question of ''automatic standardization'' of Arabic dialects for machine translation. Here we distinguish between rule-based machine translation…

Since their inception, transformer-based language models have led to impressive performance gains across multiple natural language processing tasks. For Arabic, the current state-of-the-art results on most datasets are achieved by the…

Arabic dialect identification (ADI) systems are essential for large-scale data collection pipelines that enable the development of inclusive speech technologies for Arabic language varieties. However, the reliability of current ADI systems…

Speech acts are a speakers actions when performing an utterance within a conversation, such as asking, recommending, greeting, or thanking someone, expressing a thought, or making a suggestion. Understanding speech acts helps interpret the…

This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited…

A sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especially for multiple language varieties and dialects. We…

NatiQ is end-to-end text-to-speech system for Arabic. Our speech synthesizer uses an encoder-decoder architecture with attention. We used both tacotron-based models (tacotron-1 and tacotron-2) and the faster transformer model for generating…

Bengali is spoken by over 230 million people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our system for the DL Sprint 4.0 Bengali Long-Form Speech…