Error Detection in Broadcast News ASR Using Markov Chains
نویسندگان
چکیده
This article addresses error detection in broadcast news automatic transcription, as a post-processing stage. Based on the observation that many errors appear in bursts, we investigated the use of Markov Chains (MC) for their temporal modelling capabilities. Experiments were conducted on a large Amercian English broadcast news corpus from NIST. Common features in error detection were used, all decoder-based. MC classification performance was compared with a discriminative maximum entropy model (Maxent), currently used in our in-house decoder to estimate confidence measures, and also with Gaussian Mixture Models (GMM). The MC classifier obtained the best results, by detecting 16.2% of the errors, with the lowest classification error rate of 16.7%. To be compared with the GMM classifier, MC allowed to lower the number of false detections, by 23.5% relative. The Maxent system achieved the same CER, but detected only 7.2% of the errors.
منابع مشابه
Statistical Machine Translation of Broadcast News from Spanish to Portuguese
In this paper we describe the work carried out to develop an automatic system for translation of broadcast news from Spanish to Portuguese. Two challenging topics of speech and language processing were involved: Automatic Speech Recognition (ASR) of the Spanish News and Statistical Machine Translation (SMT) of the results to the Portuguese language. ASR of broadcast news is based on the AUDIMUS...
متن کاملDevelopment of a Speech Recognition System for Spanish Broadcast News
One of the ASR applications is the generation of transcripts to facilitate searching through multi-media collections containing spoken data. Especially in the broadcast news domain ASR systems have been successfully deployed to index large collections of news. First of all because retrieval performed on ASR generated transcripts with an word-error rate (WER) under 50% gives resonable results [1...
متن کاملComparing and Combining Modeling Techniques for Sentence Segmentation of Spoken Czech Using Textual and Prosodic Information
This paper deals with automatic sentence boundary detection in spoken Czech using both textual and prosodic information. This task is important to make automatic speech recognition (ASR) output more readable and easier for downstream language processing modules. We compare and combine three statistical models – hidden Markov model, maximum entropy, and adaptive boosting. We evaluate these metho...
متن کاملTowards Phonetically-Driven Hidden Markov Models: Can We Incorporate Phonetic Landmarks in HMM-Based ASR?
Automatic speech recognition mainly relies on hidden Markov models (HMM) which make little use of phonetic knowledge. As an alternative, landmark based recognizers rely mainly on precise phonetic knowledge and exploit distinctive features. We propose a theoretical framework to combine both approaches by introducing phonetic knowledge in a non stationary HMM decoder. To demonstrate the potential...
متن کاملTopic and style-adapted language modeling for Thai broadcast news ASR
The amount of available Thai broadcast news transcribed text for training a language model is still very limited, comparing to other major languages. Since the construction of a broadcast news corpus is very costly and time-consuming, newspaper text is often used to increase the size of training text data. This paper proposes a language model topic and style adaptation approach for a Thai broad...
متن کامل