David Llorens

Speech-to-speech translation based on finite-state transducers

Nowadays, the most successful speech recognition systems are based on stochastic finite-state networks (hidden Markov models and n-grams). Speech translation can be accomplished in a similar way as speech recognition. Stochastic finite-state transducers, which are specific stochastic finite-state networks, have proved very adequate for translation modeling. In this work a speech-to-speech translation system, the EuTRANS system, is presented. The acoustic, language and translation models are finite-state networks that are automatically learnt from training samples. This system was assessed in a series of translation experiments from Spanish to English and from Italian to English in an application involving the interaction (by telephone) of a customer with a receptionist at the front-desk of a hotel.

Text and speech translation by means of subsequential transducers

The full paper explores the possibility of using Subsequential Transducers (SST), a finite state model, in limited domain translation tasks, both for text and speech input. A distinctive advantage of SSTs is that they can be efficiently learned from sets of input-output examples by means of OSTIA, the Onward Subsequential Transducer Inference Algorithm (Oncina et al. 1993). In this work a technique is proposed to increase the performance of OSTIA by reducing the asynchrony between the input and output sentences, the use of error correcting parsing to increase the robustness of the models is explored, and an integrated architecture for speech input translation by means of SSTs is described.

FINITE STATE LANGUAGE MODELS SMOOTHED USING n-GRAMS

We address the problem of smoothing the probability distribution defined by a finite state automaton. Our approach extends the ideas employed for smoothing n-gram models. This extension is obtained by interpreting n-gram models as finite state models. The experiments show that our smoothing improves perplexity over smoothed n-grams and Error Correcting Parsing techniques.

Using knowledge to improve N-gram language modelling through the MGGI methodology

The structural limitations of N-Gram models used for Language Modelling are illustrated through several examples. In most cases of interest, these limitations can be easily overcome using (general) regular or finite-state models, without having to resort to more complex, recursive devices. The problem is how to obtain the required finite-state structures from reasonably small amounts of training (positive) sentences of the considered task. Here this problem is approached through a Grammatical Inference technique known as MGGI. This allows us to easily apply a priory knowledge about the type of syntactic constraints that are relevant to the considered task to significantly improve the performance of N-Grams, using similar or smaller amounts of training data. Speech Recognition experiments are presented with results supporting the interest of the proposed approach.

State: A Multimodal Assisted Text-Transcription System for Ancient Documents

We present a complete assisted transcription system for ancient documents: State. The system consists of two applications: a pen-based, interactive application to assist humans in transcribing ancient documents and a recognition engine which offers automatic transcriptions via a web service. The interaction model and the recognition algorithm employed in the current version of State are presented. Some preliminary experiments show the productivity gains obtained with the system when transcribing a document and the error rate of the current recognition engine.

Acoustic and syntactical modeling in the ATROS system

Current speech technology allows us to build efficient speech recognition systems. However, model learning of knowledge sources in a speech recognition system is not a closed problem. In addition, lower demand of computational requirements are crucial to building real-time systems. ATROS is an automatic speech recognition system whose acoustic, lexical, and syntactical models can be learnt automatically from training data by using similar techniques. In this paper, an improved version of ATROS which can deal with large smoothed language models and with large vocabularies is presented. This version supports acoustic and syntactical models trained with advanced grammatical inference techniques. It also incorporates new data structures and improved search algorithms to reduce the computational requirements for decoding. The system has been tested on a Spanish task of queries to a geographical database (with a vocabulary of 1,208 words).