← Search

Mohammadi Zaki

7 accepted papers

2025

Enhancing Entertainment Translation for Indian Languages Using Adaptive Context, Style and LLMs

AAAI 2025technical

We address the challenging task of neural machine translation (NMT) in the entertainment domain, where the objective is to automatically translate a given dialogue from a source language content to a target language. This task has various applications, particularly in automatic dubbing, subtitling,…

Cited by 2SourcePDFScholar
2025

Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction

NAACL 2025findings

Ensembling neural machine translation (NMT) models to produce higher-quality translations than the L individual models has been extensively studied. Recent methods typically employ a candidate selection block (CSB) and an encoder-decoder fusion block (FB), requiring inference across all candidate mo…

Cited by 1SourcePDFScholar
2025

Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic languages

ACL 2025finding

Translating multi-word expressions (MWEs) and idioms requires a deep understanding of the cultural nuances of both the source and target languages. This challenge is further amplified by the one-to-many nature of idiomatic translations, where a single source idiom can have multiple target-language e…

Cited by 0SourcePDFScholar
2024

Isometric Neural Machine Translation using Phoneme Count Ratio Reward-based Reinforcement Learning

NAACL 2024findings

Traditional Automatic Video Dubbing (AVD) pipeline consists of three key modules, namely, Automatic Speech Recognition (ASR), Neural Machine Translation (NMT), and Text-to-Speech (TTS). Within AVD pipelines, isometric-NMT algorithms are employed to regulate the length of the synthesized output text.…

2017

Quality assessment of voice converted speech using articulatory features

ICASSP 2017accepted

We propose a novel application of the acoustic-to-articulatory inversion (AAI) towards a quality assessment of the voice converted speech. The ability of humans to speak effortlessly requires the coordinated movements of various articulators, muscles, etc. This effortless movement contributes toward…

Cited by 11SourceScholar