An Automated End-to-End Open-Source Software for High-Quality Text-to-Speech Dataset Generation

1 code implementation • 26 Feb 2024 • Ahmet Gunduz, Kamer Ali Yuksel, Kareem Darwish, Golara Javadi, Fabio Minazzi, Nicola Sobieski, Sebastien Bratieres

Data availability is crucial for advancing artificial intelligence applications, including voice-based technologies.

A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision

1 code implementation • 21 Jun 2023 • Kamer Ali Yuksel, Thiago Ferreira, Ahmet Gunduz, Mohamed Al-Badrashiny, Golara Javadi

The common standard for quality evaluation of automatic speech recognition (ASR) systems is reference-based metrics such as the Word Error Rate (WER), computed using manual ground-truth transcriptions that are time-consuming and expensive to obtain.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning

1 code implementation • 21 Jun 2023 • Kamer Ali Yuksel, Thiago Ferreira, Golara Javadi, Mohamed El-Badrashiny, Ahmet Gunduz

The self-supervised NoRefER exploits the known quality relationships between hypotheses from multiple compression levels of an ASR for learning to rank intra-sample hypotheses by quality, which is essential for model comparisons.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Efficient Machine Translation Corpus Generation

1 code implementation • AMTA 2022 • Kamer Ali Yuksel, Ahmet Gunduz, Shreyas Sharma, Hassan Sawaf

In this paper, the effect of prioritizing with the proposed method on the resulting MT corpus quality is presented versus scheduling hypotheses randomly.

Machine Translation Scheduling +1

EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only

no code implementations • 20 Jun 2023 • Kamer Ali Yuksel, Ahmet Gunduz, Mohamed Al-Badrashiny, Shreyas Sharma, Hassan Sawaf

The online learning capability of this system allows for dynamic adaptation to alterations in the domain or machine translation engines, thereby obviating the necessity for additional training.

Machine Translation Sentence +1

Resource Efficient 3D Convolutional Neural Networks

2 code implementations • 4 Apr 2019 • Okan Köpüklü, Neslihan Kose, Ahmet Gunduz, Gerhard Rigoll

Recently, convolutional neural networks with 3D kernels (3D CNNs) have been very popular in computer vision community as a result of their superior ability of extracting spatio-temporal features within video frames compared to 2D CNNs.

Action Recognition In Videos Transfer Learning

Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks

5 code implementations • 29 Jan 2019 • Okan Köpüklü, Ahmet Gunduz, Neslihan Kose, Gerhard Rigoll

We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures.

Action Recognition General Classification +2