Minimum Word Error Rate Decoding
نویسنده
چکیده
From the theory of Bayesian pattern recognition it is well known that the maximum a posteriori decision criterion yields a recogniser with the minimum probability of assigning the incorrect label to a pattern, if the correct probability distributions are used. This MAP criterion is also routinely employed in automatic speech recognition system. The problem addressed in this thesis is the fact that in a continuous speech recognition task the MAP criterion only guarantees to minimise the sentence error rate, but for many application the by far more relevant error metric is the word error rate. In the general framework of lattice rescoring an approach is investigated that tries to directly use the word error metric in the objective function that is the basis of the decision in the recogniser. An implementation of two variants of this approach is presented and its performance is evaluated on two very different continuous speech corpora. Closely related to this is the problem of replacing the a posteriori probabilities based on whole sentences that are used in conventional decoders by posterior probabilities on the word level. A new technique of estimating these word posteriors is presented and applied with the aim of improving the decoding result and also providing accurate confidence scores.
منابع مشابه
Minimum hypothesis phone error as a decoding method for speech recognition
In this paper we show how methods for approximating phone error as normally used for Minimum Phone Error (MPE) discriminative training, can be used instead as a decoding criterion for lattice rescoring. This is an alternative to Confusion Networks (CN) which are commonly used in speech recognition. The standard (Maximum A Posteriori) decoding approach is a Minimum Bayes Risk estimate with respe...
متن کاملMinimum Bayes-Risk Decoding cons for Information Retrie
The paper addresses a new evaluation measure of automatic speech recognition (ASR) and a decoding strategy oriented for speech-based information retrieval (IR). Although word error rate (WER), which treats all words in a uniform manner, has been widely used as an evaluation measure of ASR, significance of words are different in speech understanding or IR. In this paper, we define a new ASR eval...
متن کاملRisk based lattice cutting for segmental minimum Bayes-risk decoding
Minimum Bayes Risk (MBR) decoders improve upon MAP decoders by directly optimizing loss function of interest: Word Error Rate MBR decoding is expensive when the search spaces are large Segmental MBR (SMBR) decoding breaks the single utterance-level MBR decoder into a sequence of simpler search problems. – To do this, the N-best lists or lattices need to be segmented We present: A new lattice se...
متن کاملConversational telephone speech recognition
This paper describes the development of a speech recognition system for the processing of telephone conversations, starting with a state-of-the-art broadcast news transcription system. We identify major changes and improvements in acoustic and language modeling, as well as decoding, which are required to achieve state-of-theart performance on conversational speech. Some major changes on the aco...
متن کاملSupport Vector Machines for Segmental Minimum Bayes Risk Decoding
Segmental Minimum Bayes Risk (SMBR) Decoding is an approach whereby we use a decoding criterion that is closely matched to the evaluation criterion (Word Error Rate) for speech recognition. This involves the refinement of the search space into manageable confusion sets (ie, smaller sets of confusable words). We propose using Support Vector Machines (SVMs) as a discriminative model in the refine...
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 1999