Spoken Web Search using an Ergodic Hidden Markov Model of Speech
نویسندگان
چکیده
An ergodic hidden Markov model (EHMM) of speech can be trained in an unsupervised manner using unlabeled speech. A keyword spotting system has been developed where the queries and test observations are represented as sequences of states of the EHMM. A graphical keyword model is built by aggregating multiple instances of a query or by using mappings between phonemes and states of the EHMM. A modified Viterbi algorithm with a 3D lattice structure has been used to score the observations.
منابع مشابه
A study of applying Vietnamese voice interaction for a context-aware aviation search engine
Voice searching is the technology underlying in many spoken dialog applications that enable users to access information using spoken queries. With some popular languages like English etc, voice search function is able to help user to search complex voice queries thanks to long time researches for those languages. For Vietnamese language, voice searching has been researched and its results bring...
متن کاملSpeech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملText to Phoneme Conversion in Persian Using Smooth Ergodic Hidden Markov Model
In developing a text-to-speech system, it is well known that the accuracy of information extracted from a text is crucial to produce high quality synthesized speech. In this paper, a Persian text to speech system is studied. The system uses speech waveform concatenation method that is comparatively mature in text-to-speech synthesis. This paper describes the innovation introduced into the text ...
متن کاملSpeaker Independent Phonetic Transcription of Fluent Speech for Large Vocabulary Speech Recognition
Speaker independent phonetic Iranscription of fluent speech is performed using an ergodic continuously variable duration hidden Markov model (CVDHMM) to represent the acoustic, phonetic and phonotactic structure of speech. An important property of the model is that each of its fifty-one states is uniquely identified with a single phonetic unit. Thus, for any spoken utterance, a phonetic transcr...
متن کاملUnsupervised Hidden Markov Modeling of Spoken Queries for Spoken Term Detection without Speech Recognition
We propose an unsupervised technique to model the spoken query using hidden Markov model (HMM) for spoken term detection without speech recognition. By unsupervised segmentation, clustering and training, a set of HMMs, referred to as acoustic segment HMMs (ASHMMs), is generated from the spoken archive to model the signal variations and frame trajectories. An unsupervised technique is also desig...
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 2013