Search

This paper deals with a description of NaniTrans, a tool for segmentation and labeling of speech. The tool is programmed to work on the MATLAB application interface, in any of the supported platforms (Unix, Windows, Macintosh). The tool has been designed to annotate large speech databases, which can be also partially preprocessed (but require manual supervision). It supports the definition of an environment of annotation: set of annotation levels (orthographic, phonetic, etc.), display mode (how to show information), graphic representation (waveform, spectrogram), keyboard short-cuts, etc. This configuration is then used on a speech database. A safe file locking system allows many annotators to work concurrently on the same speech database. The tool is very friendly and easy to use by non experienced annotators, and it is designed to optimize speed using both keyboard and mouse. New options or speech processing tools can be easily added by using any MATLAB or user defined function.

Under the SpeechDat specifications, the Spanish member of SpeechDat consortium has recorded a Catalan database that includes one thousand speakers. This communication describes some experimental work that has been carried out using both the Spanish and the Catalan speech material. A speech recognition system has been trained for the Spanish language using a selection of the phonetically balanced utterances from the 4500 SpeechDat training sessions. Utterances with mispronounced or incomplete words and with intermittent noise were discarded. A set of 26 allophones was selected to account for the Spanish sounds and clustered demiphones have been used as context dependent sub-lexical units. Following the same methodology, a recognition system was trained from the Catalan SpeechDat database. Catalan sounds were described with 32 allophones. Additionally, a bilingual recognition system was built for both the Spanish and Catalan languages. By means of clustering techniques, the suitable set of allophones to cover simultaneously both languages was determined. Thus, 33 allophones were selected. The training material was built by the whole Catalan training material and the Spanish material coming from the Eastern region of Spain (the region where Catalan is spoken). The performance of the Spanish, Catalan and bilingual systems were assessed under the same framework. The Spanish system exhibits a significantly better performance than the rest of systems due to its better training. The bilingual system provides an equivalent performance to that afforded by both language specific systems trained with the Eastern Spanish material or the Catalan SpeechDat corpus.

It is well known that canonical Spanish, the dialectal variant `central' of Spain, so called Castilian, can be transcribed by rules. This paper deals with the automatic grapheme to phoneme transcription rules in several Spanish dialects from Latin America. Spanish is a language spoken by more than 300 million people, has an important geographical dispersion compared among other languages and has been historically influenced by many native languages. In this paper authors expand the Castilian transcription rules to a set of different dialectal variants of Latin America. Transcriptions are based on SAMPA symbols. The paper includes an identification of sounds that doesn't appear in Castilian, extend accepted SAMPA symbols for Spanish (Castilian) to different dialectal variants, describes the necessary rules to implement an automatic Orthographic to Phonetic transcription in several dialectal Spanish variants and show some quantitative results of dialectal differences.

In this paper we are addressed to the problem of speech presence and silences detection. Speech signals possess properties to which higher order statistics are sensitive. Bispectral-based statistics have been proved a good alternative [3] to energy-based statistics in a speech presence detector scheme, but at the cost of computations. Three alternative methods are proposed for a reliable and more computationally efficient detection. Two, lag-and frequency-domain, methods for the computation of the IT and the OT contribution to total skew while keeping the ability of the statistic in [3]. And a method based in the integrated polyspectrum (IP).

This paper deals with the application of Higher Order Statistics (HOS) in speech coding. A new model for speech production is implemented and the parameters of the vocal track are obtained from a linear combination of third order cumulants of the speech signal. Noisy signals have been used to test the system including colored Gaussian noise and sinusoidal interfering signals. Pitch and voicing decision are also obtained by HOS analysis of speech.

This paper describes the phonetic content of Albayzin, a spoken database for Spanish designed for speech recognition purposes. A statistical study of a large sample of spontaneous speech is presented, and the phonetic and statistical criteria for the final constitution of the database are discussed. Finally, the contents of the phonetic database are analyzed

This paper describes an application for automatic speechdatabases acquisition (ADA) developed by the authors in the framework of the EC Telematics Project SpeechDat II. The software is able to work with standard inexpensive PC cards for ISDN lines, as well as Dialogic Boards for analogue telephone lines. Both program versions share a common file format and configuration. Other important characteristics of the recording software are its simple set-up, a fast and flexible configuration of the recording session, the real-time monitoring of calls and disk space, and its proven robustness.