Obiettivo
The aim of the SPRINT Action was to examine whether connectionist techniques can be used to improve the current performance of automatic speech recognition systems, with particular respect to speaker independence and noise insensitivity.
Answers were sought to the following questions:
-How can the recogniser be provided with robust features adapted to new speakers or environments?
-How can acoustic parameters be mapped onto phonetic symbols using different neural network paradigms?
-How can the competitive learning approach be applied to high-level speech processing in order to understand the lexicon structures?
-How can isolated words be recognised, considering the problems related to time-varying word patterns and noise immunity?
Various unsolved problems in speech recognition were tackled by exploring the distinctive features of neural networks (eg, non-linearity, self-organisation, parallelism) to upgrade the performance of automatic speech recognition systems. The connectionist paradigms were exploited to investigate some of the problems in relationship with speech variabilities: adaption to new speakers and/or new environments, noise immunity, classification of speech parameters using a set of phonetic symbols, and recognition of isolated words (lexical access). Theoretical studies have been conducted to establish the capabilities of various neural networks to generate any spectral transformation. For each network architecture, the ability to discriminate between several classes during classification was also evaluated. The evaluation of speaker adaption procedures based on learning spectral transformation with multilayer perceptrons was conducted. Well established methods were compared. The use of neural networks to carry out the transformations of speech parameters, necessary for recognition that is robust with respect to speech signals contaminated by background noise was investigated. Preliminary experiments have been carried out. Evaluation of very simple structures of perceptions: sparsely connected neural nets (neural nets with different topologies: local connection (TDNN), scally or fully connected) for spectra and isolated work classification was conducted. These experiments showed the need for specifically designed networks. Experiments with LVQ alone, a TDNN-derived network alone and combined TDNN-LVQ architectures proved the combined architecture to be the most efficient. An examination was made of the scally network topology for noise robustness and for use with various approaches to time alignment. The use of added noise in training to improve generalisation was investigated. An information theoretic distance metric was developed, together with a multilayer perception which has outputs with a probabilistic interpretation.
APPROACH AND METHODS
The speech representation levels considered are signal, parameter, phonetic and lexical. The main areas of investigation were:
-The transition from the signal to the parameter level and transitions within the parameter level: research will provide the recognition system with a set of parameters leading to the best performance. Transformations of classical speech representationsare investigated, based on multi-layer perceptrons, topological maps, and the learning vector quantification method.
-The transition from the parameter to the phonetics level: various feed-forward neural network topologies have been assessed, and some found to integrate prior knowledge.
-The transition from the phonetic to the (sub)lexical level: the competitive learning approach is used to determine the structure of the lexicon and the structure between morpheme units and the phonemes.
-The transition from the parameter to the lexical level: the ability of various network paradigms to learn to generalise has been examined in order to deal with intra and inter-speaker variability and background noise. The problem of recognising time-var ying speech patterns has been approached by transforming the speech signal to fit the fixed size network input layer. Architectures and hybrid systems that integrate neural networks with well-established approaches are used.
PROGRESS AND RESULTS - STATUS OF OCTOBER 1991
The available deliverables report on the following research activities:
-Theoretical studies have been conducted to establish the capabilities of various neural networks to generate any spectral transformation. For each network architecture, the ability to discriminate between several classes during classification was also e valuated.
-The evaluation of speaker adaptation procedures based on learning spectral transformation with multi-layer perceptrons. Well-established methods were compared.
-The use of neural networks to carry out the transformations of speech parameters, necessary for recognition that is robust with respect to speech signals contaminated by background noise. Preliminary experiments have been carried out.
-Evaluation of very simple structures of perceptions: SPARSELY connected neural nets (Neural nets with different topologies: local connection (TDNN), scally or fully connected) for spectra and isolated word classification is conducted. These experimentsshow the need for specifically designed networks. Experiments with LVQ alone, a TDNN-derived network alone and combined TDNN-LVQ architectures proved the combined architecture to be the most efficient.
-An examination of the scally network topology for noise robustness and for use with various approaches to time alignment.
-The use of added noise in training to improve generalisation.
-The development of an information theoretic distance metric together with a multilayer perception which has outputs with a probabilistic interpretation, unifying the probabilistically forma hidden Markov modelling techniques and multilayer perception ap proaches, and leading to the development of an HMM-MLP hybrid.
POTENTIAL
The basic know-how acquired and the tools developed will be used in the next step to meet the challenge of integrating these techniques within an automatic speech recogniser. Furthermore, this work will be exploited in other areas such as pattern recognition (image, fonts, characters).
Campo scientifico (EuroSciVoc)
CORDIS classifica i progetti con EuroSciVoc, una tassonomia multilingue dei campi scientifici, attraverso un processo semi-automatico basato su tecniche NLP. Cfr.: Il Vocabolario Scientifico Europeo.
CORDIS classifica i progetti con EuroSciVoc, una tassonomia multilingue dei campi scientifici, attraverso un processo semi-automatico basato su tecniche NLP. Cfr.: Il Vocabolario Scientifico Europeo.
- scienze naturali matematica matematica pura topologia
- ingegneria e tecnologia ingegneria elettrica, ingegneria elettronica, ingegneria informatica ingegneria informatica telecomunicazioni reti di telecomunicazione
- scienze umanistiche lingue e letteratura linguistica fonetica
- scienze naturali informatica e scienze dell'informazione intelligenza artificiale riconoscimento delle forme
- scienze naturali informatica e scienze dell'informazione intelligenza artificiale intelligenza computazionale
È necessario effettuare l’accesso o registrarsi per utilizzare questa funzione
Programma(i)
Programmi di finanziamento pluriennali che definiscono le priorità dell’UE in materia di ricerca e innovazione.
Programmi di finanziamento pluriennali che definiscono le priorità dell’UE in materia di ricerca e innovazione.
Argomento(i)
Gli inviti a presentare proposte sono suddivisi per argomenti. Un argomento definisce un’area o un tema specifico per il quale i candidati possono presentare proposte. La descrizione di un argomento comprende il suo ambito specifico e l’impatto previsto del progetto finanziato.
Dati non disponibili
Gli inviti a presentare proposte sono suddivisi per argomenti. Un argomento definisce un’area o un tema specifico per il quale i candidati possono presentare proposte. La descrizione di un argomento comprende il suo ambito specifico e l’impatto previsto del progetto finanziato.
Invito a presentare proposte
Procedura per invitare i candidati a presentare proposte di progetti, con l’obiettivo di ricevere finanziamenti dall’UE.
Dati non disponibili
Procedura per invitare i candidati a presentare proposte di progetti, con l’obiettivo di ricevere finanziamenti dall’UE.
Meccanismo di finanziamento
Meccanismo di finanziamento (o «Tipo di azione») all’interno di un programma con caratteristiche comuni. Specifica: l’ambito di ciò che viene finanziato; il tasso di rimborso; i criteri di valutazione specifici per qualificarsi per il finanziamento; l’uso di forme semplificate di costi come gli importi forfettari.
Meccanismo di finanziamento (o «Tipo di azione») all’interno di un programma con caratteristiche comuni. Specifica: l’ambito di ciò che viene finanziato; il tasso di rimborso; i criteri di valutazione specifici per qualificarsi per il finanziamento; l’uso di forme semplificate di costi come gli importi forfettari.
Dati non disponibili
Coordinatore
38240 Meylan
Francia
I costi totali sostenuti dall’organizzazione per partecipare al progetto, compresi i costi diretti e indiretti. Questo importo è un sottoinsieme del bilancio complessivo del progetto.