Jaume Padrell

Robust speech activity detection using LDA applied to FF parameters

Speech detection becomes more complicated when performed in noisy and reverberant environments like e.g. smart rooms. In this work, we design a robust speech activity detection (SAD) algorithm and we evaluate it on distant microphone signals acquired in a smart room-like environment. The algorithm is based on a measure obtained from applying linear discriminant analysis (LDA) on frequency filtering (FF) features. With a time sequence of this measure, a decision tree based speech/non-speech classifier is trained. The proposed SAD system is evaluated together with other SAD systems (GSM SAD and ETSI advanced front-end standard SAD) using a set of general SAD metrics as well as using the ASR accuracy as a metric. The proposed SAD algorithm shows better average results than the other tested SAD systems for both the set of general SAD metrics and the ASR performance.

A Speech-to-Speech Translation System for Catalan, Spanish, and English

In this paper we describe the FAME interlingual speech-to- speech translation System for Spanish, Catalan and English which is intended to assist users in the reservation of a hotel room when calling or visiting abroad. The System has been developed as an extension of the existing NESPOLE! translation system [4] which translates between English, German, Italian and French. After a brief introduction we describe the Spanish and Catalan System components including speech recognition, transcription to IF mapping, IF to text generation and speech synthesis. We also present a task-oriented evaluation method used to inform about system development and some preliminary results.

Frequency averaging: an useful multiwindow spectral analysis approach

The multiwindow approach is a meaningful framework for nonparametric spectral estimation. It also encompasses several conventional methods as WOSA and frequency-averaged periodogram. Recently, some authors claimed that the Slepian windows of Thomsons method and other related optimal sets of windows show a better performance in terms of resolution, variance and leakage. In this paper, that claim is discussed by means of some simulation examples and by applying the various methods to speech recognition. In conclusion, frequency averaging of the periodogram is a computationally simple method that has a great flexibility for band specification and comparatively shows good performance. In fact, it is the spectral analysis technique most extensively employed for speech recognition.

Architecture and dialogue design for a voice operated information system

In this paper we present a real automatic meteorological information system that, not only provides friendly voice access to real-time data coming from automatic sensors, but also establishes an automatic warning service on the weather. It aims to extend the availability, personalization and friendliness of the meteorological information by means of a reusable easy-to-use friendly oral natural language interface. This interface takes advantage of the improvements in speech processing, dialogue handling and the great growth of mobile telephony. After the description of the functionalities of the system and its architecture, we present in detail the features of the dialogue manager. The main goals we have considered are: to provide the right information and to design a friendly interface.