• Home
  • Luis Rodríguez-Ruiz
Luis Rodríguez-Ruiz

Luis Rodríguez-Ruiz
Fluent.ai

PhD in Computer Science

About

45
Publications
5,049
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
340
Citations
Introduction
I work as a senior machine learning scientist at Fluent.ai in Montreal, Canada. My current research is focused on deep learning approaches for robust speech recognition.
Additional affiliations
February 2018 - present
Fluent.ai
Position
  • Researcher
September 2005 - January 2018
University of Castilla-La Mancha
Position
  • Professor (Assistant)
February 2003 - September 2005

Publications

Publications (45)
Article
Nowadays, information retrieval systems are widely available and routinely used by many non-skilled computer users. Therefore, user interfaces have to be simple, natural and, above all, they should not require any technical knowledge. To this end, an architecture to develop interactive systems that allow users to access to databases using natural l...
Conference Paper
Speech recognition systems are not typically able to produce error-free results in real scenarios. On account of this, human intervention is usually needed. This intervention can be included into the system by following the Computer Assisted Speech Transcription (CAST) approach, where the user constantly interacts with the system during the transcr...
Article
Current machine translation systems are far from being perfect. However, such systems can be used in computer-assisted translation to increase the productivity of the (human) translation process. The idea is to use a text-to-text translation system to produce portions of target language text that can be accepted or amended by a human translator usi...
Article
Indoor scene classification is usually approached from a computer vision perspective. However, in some fields like robotics, additional constraints must be taken into account. Specifically, in systems with low resources, state-of-the-art techniques (CNNs) cannot be successfully deployed. In this paper, we try to close this gap between theoretical a...
Article
Full-text available
Traditionally, the indoor scene classification problem has been approached from a 2D image recognition point of view. In most visual scene classification systems, a descriptor for the input image is generated to obtain a suitable representation that includes features related to color, shape or spatial information. Techniques based on the use of a s...
Conference Paper
In robotics, simulation plays a fundamental role for testing the models and techniques in a controlled environment prior to conducting experiments on real physical agents. In addition, some kind of scenarios can be easily reproduced within a simulator which is not always possible with a real robot. Building simulation environments, however, can be...
Conference Paper
Detection of keypoints in an image is a crucial step in most registration and recognition tasks. The information encoded in RGB-D images can be redundant and, usually, only specific areas in the image are useful for the classification process. The process of identifying those relevant areas is known as keypoint detection. The use of keypoints can f...
Conference Paper
Full-text available
Semantic localization describes the surrounding of a robot by using semantic labels. These labels are used to identify neighboring objects , but also the category of the place where the robot is located. Mul-timodal human-robot interaction refers to the communication between humans and robots by means of several information sources. This paper pres...
Article
Full-text available
This paper introduces a taxonomy of vision systems for ground mobile robots. In the last five years, a significant number of relevant papers have contributed to this subject. Firstly, a thorough review of the papers is proposed to discuss and classify both past and the most current approaches in the field. As a result, a global picture of the state...
Conference Paper
Full-text available
Developing a simple multimodal interaction game with a 31 dof's mobile manipulator can become a challenging enterprise. A conceptually simple task quickly unfolds into a rather complex ensemble of driver-oriented, framework-based, software-enabled, state-machine controlled mechatronics. In this paper we propose a multimodal interaction game designe...
Conference Paper
Full-text available
This paper is concerned with combining models for decoding an optimum translation for a dictation based machine aided human translation (MAHT) task. Statistical language model (SLM) probabilities in automatic speech recognition (ASR) are updated using statistical machine translation (SMT) model probabilities. The effect of this procedure is evaluat...
Article
Full-text available
The Workshop of Physical Agents intends to be a forum for information and experience exchange in different areas regarding the concept of agent in physical environments, especially applied to the control and coordination of autonomous systems: robots, mobile robots, industrial processes or complex systems. This special issue is devoted to the selec...
Conference Paper
Interactive machine translation (IMT) is an increasingly popular paradigm for semi-automated machine translation, where a human expert is integrated into the core of an automatic machine translation system. The human expert interacts with the IMT system by partially correcting the errors of the system's output. Then, the system proposes a new solut...
Conference Paper
We present an interactive text generation system aimed at providing assistance for text typing in different environments. This system works by predicting what the user is going to type based on the text he or she typed previously. A multimodal interface is included, intended to facilitate the text generation in constrained environments. The prototy...
Conference Paper
Interactive text generation is aimed at facilitating text generation in those situations where text typing is somehow constrained. This approach achieves a significant amount of typing effort reduction in most tasks. Natural language based interfaces for information retrieval constitute a good scenario to include this kind of assistance in order to...
Article
In statistical machine translation, an alignment defines a mapping between the words in the source and in the target sentence. Alignments are used, on the one hand, to train the statistical models and, on the other, during the decoding process to link the words in the source sentence to the words in the partial hypotheses generated. In both cases,...
Conference Paper
To date, automatic handwriting recognition systems are far from being perfect and often they need a post editing where a human intervention is required to check and correct the results of such systems. We propose to have a new interactive, on-line framework which, rather than full automation, aims at assisting the human in the proper recognition- t...
Conference Paper
Grounded in the interactive–predictive transcription framework drawn in the previous chapter, an interactive approach for efficient transcription of handwritten text images, along with its more ergonomic and multimodal variants are presented. All these approaches, rather than full automation, aim at assisting the expert in the proper transcription...
Conference Paper
Pattern Recognition systems are not error-free. Human intervention is typically needed to verify and/or correct the result of such systems. To formalize this fact, a new framework, which integrates the human activity into the recognition process taking advantage of the user’s feedback, is described. Several applications, involving Interactive Speec...
Conference Paper
Automatic Speech Recognition has been widely employed in the last years. However, when a perfect transcription of the input is required, it is still necessary to rely on a human operator that supervises and corrects the mistakes that recognition systems usually make. Although the use of automatic systems can speed up the transcription process signi...
Article
Full-text available
In statistical machine translation, an align-ment defines a mapping between the words in the source and in the target sen-tence. Alignments are used, on the one hand, to train the statistical models and, on the other, during the decoding process to link the words in the source sentence to the words in the partial hypotheses generated. In both cases...
Conference Paper
Full-text available
Speech recognition systems are usually speaker-inde- pendent, but they are not as good as speaker-dependent systems for specific speakers. An initial speaker-inde- pendent system can be adapted, transforming it into a speaker-dependent system. This is done to improve the recognition accuracy. In this work, a new general acous- tic model adaptation...
Conference Paper
Computer-Assisted Translation systems can be used by human translators to increase their productivity. In these systems, the computer suggests portions of target sentence that can be accepted or amended by a human translator. In the present work we will introduce speech as a novel way to interact with these systems. The rational behind this approac...
Article
Full-text available
TransType2 es un proyecto enmarcado en el ámbito de la traducción asistida. Su objetivo consiste en proporcionar traducciones de alta calidad combinando la experiencia de traductores humanos con sistemas de traducción automática. TransType2 is a project framed in assisted translation field. Its purpose is to provide high-quality translations by com...
Article
Full-text available
This thesis is about Pattern Recognition. In the last decades, huge efforts have been made to develop automatic systems able to rival human capabilities in this field. Although these systems achieve high productivity rates, they are not precise enough in most situations. Humans, on the contrary, are very accurate but comparatively quite slower. Thi...

Network

Cited By

Projects

Project (1)