STATISTICAL PARSING FOR SPEECH RECOGNITION, or HOW I CAME BACK FROM A WORKSHOP WITH SOMETHING NEW TO WORK ON
نویسنده
چکیده
All of this became clearer to me after a recent workshop at the Institute for Mathematics and Its Applications at the University of Minnesota. The conference was intended to bring together three groups of people who have overlapping interests but seldom attend the same standard academic conferences. I am a member of the “computational linguistics” clan. As a group we are interested in applying computers to problems in language. Most of us would see as our ultimate goal getting a computer to
منابع مشابه
Statistical Variation Analysis of Formant and Pitch Frequencies in Anger and Happiness Emotional Sentences in Farsi Language
Setup of an emotion recognition or emotional speech recognition system is directly related to how emotion changes the speech features. In this research, the influence of emotion on the anger and happiness was evaluated and the results were compared with the neutral speech. So the pitch frequency and the first three formant frequencies were used. The experimental results showed that there are lo...
متن کامل1 A Hidden Tag Model for LanguageE
During the LM95 workshop, the \parse group" explored ideas on improving the language model by incorporating linguistic structure of language. The group worked on 3 related activities during the summer: development of a new Hidden Tag Model for language, initial exploration of parsing switchboard transcripts, and development of keyword selection methods for topic identiication. Most of our work ...
متن کاملتصحیح خودکار خطا در درخت بانک نحوی با استفاده از یادگیری ماشینی انتقال محور
The Treebank is one of the most useful resources for supervised or semi-supervised learning in many NLP tasks such as speech recognition, spoken language systems, parsing and machine translation. Treebank can be developded in different ways that could be, generally, categorized in manually and statistical approaches. While the resulted Treebank in each of these methods has the annotation error,...
متن کاملروشی جدید در بازشناسی مقاوم گفتار مبتنی بر دادگان مفقود با استفاده از شبکه عصبی دوسویه
Performance of speech recognition systems is greatly reduced when speech corrupted by noise. One common method for robust speech recognition systems is missing feature methods. In this way, the components in time - frequency representation of signal (Spectrogram) that present low signal to noise ratio (SNR), are tagged as missing and deleted then replaced by remained components and statistical ...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کامل