In this work, we are concerned with a coarse grained semantic analysis over sparse data, which labels all nouns with a set of semantic categories. To get the benefit of unlabeled data, we propose a bootstrapping frame...
详细信息
Voice Onset Time (VOT) is an important temporal feature in speech perception and speech recognition. It also benefits for accent detection[1,2]. Fixed length frame based speechprocessing inherently ignores VOT. In th...
详细信息
Voice Onset Time (VOT) is an important temporal feature in speech perception and speech recognition. It also benefits for accent detection[1,2]. Fixed length frame based speechprocessing inherently ignores VOT. In this paper we propose a more effective VOT detection scheme using the non-linear energy tracking algorithm (Teager Energy Operator (TEO)) across a sub-frequency band partition for unvoiced stops (p, t and k). The VOT detection algorithm is applied to the problem of accent classification. Three different language groups (Indian, Chinese and American English) are used from CU-Accent-Corpus to compare VOT's of both accented and native American English. Some pathological cases are considered where speakers have breathy voices or other issues in recording procedure. The VOT is detected with less than 10% error when compared to the manual detected VOT. Also, pairwise English accent classification are 87% for Chinese accent, 80% for English accent, and 47% for Indian accent (includes atypical cases for Indian case).
In this paper, we explore the use of Random Forests (RFs) in the structured language model (SLM), which uses rich syntactic information in predicting the next word based on words already seen. The goal in this work is...
In this paper, we explore the use of Random Forests (RFs) in the structured language model (SLM), which uses rich syntactic information in predicting the next word based on words already seen. The goal in this work is to construct RFs by randomly growing Decision Trees (DTs) using syntactic information and investigate the performance of the SLM modeled by the RFs in automatic speech ***, which were originally developed as classifiers, are a combination of decision tree classifiers. Each tree is grown based on random training data sampled independently and with the same distribution for all trees in the forest, and a random selection of possible questions at each node of the decision tree. Our approach extends the original idea of RFs to deal with the data sparseness problem encountered in language *** have been studied in the context of n-gram language modeling and have been shown to generalize well to unseen data. We show in this paper that RFs using syntactic information can also achieve better performance in both perplexity (PPL) and word error rate (WER) in a large vocabulary speech recognition system, compared to a baseline that uses Kneser-Ney smoothing.
The paper presents a method of automatic enrichment of a very large dictionary of word combinations. The method is based on results of automatic syntactic analysis (parsing) of sentences. The dependency formalism is u...
详细信息
Much is known about the design of automated systems to search broadcast news, but it has only recently become possible to apply similar techniques to large collections of spontaneous speech. This paper presents initia...
详细信息
Much is known about the design of automated systems to search broadcast news, but it has only recently become possible to apply similar techniques to large collections of spontaneous speech. This paper presents initial results from experiments with speech recognition, topic segmentation, topic categorization, and named entity detection using a large collection of recorded oral histories. The work leverages a massive manual annotation effort on 10 000 h of spontaneous speech to evaluate the degree to which automatic speech recognition (ASR)-based segmentation and categorization techniques can be adapted to approximate decisions made by human annotators. ASR word error rates near 40% were achieved for both English and Czech for heavily accented, emotional and elderly spontaneous speech based on 65-84 h of transcribed speech. Topical segmentation based on shifts in the recognized English vocabulary resulted in 80% agreement with manually annotated boundary positions at a 0.35 false alarm rate. Categorization was considerably more challenging, with a nearest-neighbor technique yielding F = 0.3. This is less than half the value obtained by the same technique on a standard newswire categorization benchmark, but replication on human-transcribed interviews showed that ASR errors explain little of that difference. The paper concludes with a description of how these capabilities could be used together to search large collections of recorded oral histories.
Forward decoding kernel machines (FDKM) combine large-margin classifiers with hidden Markov models (HMM) for maximum a posteriori (MAP) adaptive sequence estimation. State transitions in the sequence are conditioned o...
详细信息
ISBN:
(纸本)0262025507
Forward decoding kernel machines (FDKM) combine large-margin classifiers with hidden Markov models (HMM) for maximum a posteriori (MAP) adaptive sequence estimation. State transitions in the sequence are conditioned on observed data using a kernel-based probability model trained with a recursive scheme that deals effectively with noisy and partially labeled data. Training over very large datasets is accomplished using a sparse probabilistic support vector machine (SVM) model based on quadratic entropy, and an on-line stochastic steepest descent algorithm. For speaker-independent continuous phone recognition, FDKM trained over 177,080 samples of the TIMET database achieves 80.6% recognition accuracy over the full test set, without use of a prior phonetic language model.
We previously proposed (Kamm and Meyer (2001, 2002)) a two-pronged approach to improve system performance by selective use of training data. We demonstrated a sentence-selective algorithm that, first, made effective u...
详细信息
We previously proposed (Kamm and Meyer (2001, 2002)) a two-pronged approach to improve system performance by selective use of training data. We demonstrated a sentence-selective algorithm that, first, made effective use of the available humanly transcribed training data and, second, focused future human transcription effort on data that was more likely to improve system performance. We now extend that algorithm to focus on word selection, and demonstrate that we can reduce the error rate from 10.3 % to 9.3 % on a simple, 36-word corpus, by selecting 30 % (15 hours) of the 50 hours of training data available in this corpus, without knowledge of the true transcription. We also discuss application of our word selection algorithm to the Wall Street Journal 5 K word task. Preliminary results show that we can select up to 60 % (48 hours) of the training data, with minimal knowledge of the true transcription, and match or beat the error rate of a system built using the same amount of randomly selected training data.
This paper presents a comprehensive empirical exploration and evaluation of a diverse range of data characteristics which influence word sense disambiguation performance. It focuses on a set of six core supervised alg...
暂无评论