Word error rate

About: Word error rate is a research topic. Over the lifetime, 11939 publications have been published within this topic receiving 298031 citations.

Error correction for speech recognition systems

Abstract: Words in a sequence of words that is obtained from speech recognition of an input speech sequence are presented to a user, and at least one of the words in the sequence of words is replaced, in case it has been selected by a user for correction. Words with a low recognition confidence value are emphasized; alternative word candidates for the at least one selected word are ordered according to an ordering criterion; after replacing a word, an order of alternative word candidates for neighboring words in the sequence is updated; the replacement word is derived from a spoken representation of the at least one selected word by speech recognition with a limited vocabulary; and the word that replaces the at least one selected word is derived from a spoken and spelled representation of the at least one selected word.

Heterogeneous acoustic measurements and multiple classifiers for speech recognition

Abstract: The acoustic-phonetic modeling component of most current speech recognition systems calculates a small set of homogeneous frame-based measurements at a single, fixed time-frequency resolution. This thesis presents evidence indicating that recognition performance can be significantly improved through a contrasting approach using more detailed and more diverse acoustic measurements, which we refer to as heterogeneous measurements. This investigation has three principal goals. The first goal is to develop heterogeneous acoustic measurements to increase the amount of acoustic-phonetic information I extracted from the speech signal. Diverse measurements are obtained by varying the time-frequency resolution, the spectral representation, the choice of temporal basis vectors, and other aspects of the preprocessing of the speech waveform. The second goal is to develop classifier systems for successfully utilizing high-dimensional heterogeneous acoustic measurement spaces. This is accomplished through hierarchical and committee-based techniques for combining multiple classifiers. The third goal is to increase understanding of the weaknesses of current automatic phonetic classification systems. This is accomplished through perceptual experiments on stop consonants which facilitate comparisons between humans and machines. Systems using heterogeneous measurements and multiple classifiers were evaluated in phonetic classification, phonetic recognition, and word recognition tasks. On the TIMIT core test set, these systems achieved error rates of 18.3% and 24.4% for, context-independent phonetic classification and context-dependent phonetic recognition, respectively. These results are the best that we have seen reported on these tasks. Word recognition experiments using the corpus associated with the JUPITER telephone-based weather information system showed 10–16% word error rate reduction, thus demonstrating that these techniques generalize to word recognition in a telephone-bandwidth acoustic environment. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

Using Conditional Random Fields for Sentence Boundary Detection in Speech

Abstract: Sentence boundary detection in speech is important for enriching speech recognition output, making it easier for humans to read and downstream modules to process. In previous work, we have developed hidden Markov model (HMM) and maximum entropy (Maxent) classifiers that integrate textual and prosodic knowledge sources for detecting sentence boundaries. In this paper, we evaluate the use of a conditional random field (CRF) for this task and relate results with this model to our prior work. We evaluate across two corpora (conversational telephone speech and broadcast news speech) on both human transcriptions and speech recognition output. In general, our CRF model yields a lower error rate than the HMM and Maxent models on the NIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers. This probably occurs because each model has different strengths and weaknesses for modeling the knowledge sources.

Rates of convergence in active learning

Abstract: We study the rates of convergence in generalization error achievable by active learning under various types of label noise. Additionally, we study the general problem of model selection for active learning with a nested hierarchy of hypothesis classes and propose an algorithm whose error rate provably converges to the best achievable error among classifiers in the hierarchy at a rate adaptive to both the complexity of the optimal classifier and the noise conditions. In particular, we state sufficient conditions for these rates to be dramatically faster than those achievable by passive learning.