The spin continuous-speech decoding system
نویسندگان
چکیده
The SPIN speaker independent, continuous speech decoding system has been developed to compare several training methods as well as several decoding algorithms within a whole integrated system. This system runs on a limited application, in French. Demisyllables are used as basic sub-word units. They are extracted from the application corpus semi-automatically. Speech units are modelled by different types of HMM-based techniques. A set of D1W/Viterbi-based decoding methods is available to perform recognition of sentences. The output of the decoding process can be either a lattice of syllabic units or a single string of decoded words. The lattice output is devoted to provide an AI speech understanding system with a suitable phonetic input. An evaluation module has been designed to evaluate the potentiality of the decoded lattices. The system is fully integrated in a software graphic interface which simplifies the management of the different modules and the understanding of the various outputs.
منابع مشابه
Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition
In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the de...
متن کاملImproved Bayesian Training for Context-Dependent Modeling in Continuous Persian Speech Recognition
Context-dependent modeling is a widely used technique for better phone modeling in continuous speech recognition. While different types of context-dependent models have been used, triphones have been known as the most effective ones. In this paper, a Maximum a Posteriori (MAP) estimation approach has been used to estimate the parameters of the untied triphone model set used in data-driven clust...
متن کاملPhonetic decoding of continuous speech with the APHODEX expert system
In order to increase the accuracy of continuous speech acousticphonetic decoding, we started the APHODEX project some years ago. Our aim is to develop an expert system that implements the knowledge of an expert spectrogram reader, the phonetician F. Lonchamp. In the present version of the system, procedural and declarative approaches have been used jointly for the representation of phonetic exp...
متن کاملA fast and effective state decoding algorithm
In this paper a fast and effective algorithm named equal feature variance sum (EFVS) framesynchronous searching is presented for state decoding. EFVS controls the state transition by using only the feature variance of the speech, instead of by using the state dwell distribution. The basic hypothesis of this new algorithm is the equality of feature variance sum in each state of the speech. Given...
متن کاملA transcription-based approach to determine the difficulty of a speech recognition task
A new parameter for estimating the difficulty of a continuous speech recognition task, called speech decoding difficulty, is presented in this work. It is obtained from the language model defined for the recognition task and the phonetic similarity between the transcriptions of the words that make up the vocabulary used. Two variants of the proposed task difficulty measure are introduced: ideal...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1989