Discriminative keyword spotting

This paper describes two experiments aimed at exploring the relationship between linguistic aspects and perceived proficiency in read and spontaneous speech. 5,000 utterances of read speech by 50 non-native speakers of Korean in Experiment 1, and of 6,000 spontaneous speech utterances in Experiment 2 were scored for proficiency by native human raters and were analyzed by factors known to be related to perceived proficiency. The results show that the factors investigated in this study can be employed to predict proficiency ratings, and the predictive power of fluency and pitch and accent accuracy is strong for both read and spontaneous speech. We also observe that while proficiency ratings of read speech are mainly related to segmental accuracy, those of spontaneous speech appear to be more related to pitch and accent accuracy. Moreover, proficiency in read speech does not always equate to the proficiency in spontaneous speech, and vice versa, with Pearson’s per-speaker correlation score of 0.535.

This paper deals with an approach to Automatic Language Identification using only prosodic modeling. The actual approach for language identification focuses mainly on phonotactics because it gives the best results. We propose here to evaluate the relevance of prosodic information for language identification with read studio recording (previous experiment [1]) and spontaneous telephone speech. For read speech, experiments were performed on the five languages of the MULTEXT database [2]. On the MULTEXT corpus, our prosodic system achieved an identification rate of 79 % on the five languages discrimination task. For spontaneous speech, experiments are made on the ten languages of the OGI Multilingual telephone speech corpus [3]. On the OGI MLTS corpus, the results are given for languages pair discrimination tasks, and are compared with results from [4]. As a conclusion, if our prosodic system achieves good performance on read speech, it might not take into account the complexity of spontaneous speech prosody. 1.

The recognition of read and spontaneous speech in local vernacular: The case of Zurich German

This paper addresses the issue of producing synthetic speech for an interpreted dialogue where the attitudinal colouring of an original utterance is to be preserved; it describes differences in speaking style between read and spontaneous speech from the viewpoint of synthesis research and discusses the design of a synthesis system incorporating labels to encode the prosodic and segmental variation simultaneously. Spontaneous speech confronts us with phenomena that were not encountered in corpora of prepared or read speech, and to account for these we have to identify increasingly higher-level factors of discourse structure and speaker involvement. The paper makes three specific claims: (a) that it is better to label the distinctive characteristics of speech through higher-level context dependencies, and to select units for synthesis from appropriate contexts, rather than attempt to predict and modify fine phonetic detail; (b) that the labelling of segmental and prosodic characteristics can be done adequately for speech synthesis using automatic techniques, leaving the human labeller free to identify higher-level discourse-related aspects of the speech; and (c) that instead of minimizing the size of the source database of speech units, we should rather be concerned to maximize its variety and to efficiently select from it the units that most closely express the characteristics of the target speech. The CHATR resynthesis toolkit performs many of these tasks.

Sequence labeling to detect stuttering events in read speech

Making large-scale collections of digitized historical documents searchable is being earnestly demanded by many archives and libraries. Probabilistically indexing the text images of these collections by means of keyword spotting techniques is currently seen as perhaps the only feasible approach to meet this demand. A vast medieval manuscript collection, written in both Latin and French, called is currently being considered for indexing at large. In addition to its bilingual nature, one of the major difficulties of this collection is the very high rate of abbreviated words which, on the other hand, are completely expanded in the ground truth transcripts available. In preparation to undertake full indexing of Chancery, experiments have been carried out on a relatively small but fully representative subset of this collection. To this end, a keyword spotting approach has been adopted which computes word relevance probabilities using character lattices produced by a recurrent neural network and a N-gram character language model. Results confirm the viability of the chosen approach for the large-scale indexing aimed at and show the ability of the proposed modeling and training approaches to properly deal with the abbreviation difficulties mentioned.

Keyword spotting (KWS) is an essential technique for speech information retrieval. When doing offline keyword query on large volume spontaneous speech data, fast and accurate KWS methods are required. In this paper, a novel phone-state matrix based vocabulary-independent KWS method is proposed, which has merits of both hidden Markov model (HMM) based and lattice-based methods. Four KWS systems are compared in our experiments on conversational telephone speech test set. Result shows that compared to the high precision HMM-based KWS system the proposed phone-state matrix system has better equal-error-rate (EER) and false-alarm (FA) performance than the other two lattice-based systems.

This paper reports various investigations on recognizing spontaneous presentation speech in connection with the “Spontaneous Speech” national project started in 1999. Presentation speech uttered by 10 male speakers of approximately 4.5 hours duration has been recognized. Experimental results show that acoustic and language modeling based on an actual spontaneous speech corpus is far more effective than conventional modeling based on read speech. The recognition accuracy has a wide speaker-tospeaker variability according to the speaking rate, the number of fillers, the number of repairs, etc. It was confirmed that unsupervised speaker adaptation of acoustic models was effective to improve the recognition accuracy. The recognition accuracy for spontaneous speech is, however, still rather low, and there remains a large number of research issues.

Keyword spotting can be formulated as a non-uniform error automatic speech recognition (ASR) problem. It has been demonstrated [1] that this new formulation with the nonuniform MCE training technique can lead to improved system performance in keyword spotting applications. In this paper, we demonstrate that deep neural networks (DNNs) can be successfully trained on the non-uniform minimum classification error (MCE) criterion which weighs the errors on keywords much more significantly than those on non-keywords in an ASR task. The integration with a DNN-HMM system enables modeling of multi-frame distributions, which conventional systems find difficult to accomplish. To further improve the performance, more confusable data is generated by boosting the likelihood of the sentences that have more errors. The keyword spotting system is implemented within a weighted finite state transducer (WFST) framework and the DNN is optimized using standard backpropagation and stochastic gradient decent. We evaluate the performance of the proposed framework on a large vocabulary spontaneous conversational telephone speech dataset (Switchboard-1 Release 2). The proposed approach achieves an absolute figure of merit improvement of 3.65% over the baseline system.

Individuals who share a dialect nonetheless differ consistently in phonetic expression. The origin of such idiolectal differences has been sought in sociolinguistically and in physiologically motivated accounts. Our study focused on characteristic differences in the habitual rate of speech production within a dialect, aiming to calibrate the contribution of neuromuscular constraint in idiolect differences. We sampled and analyzed the temporal characteristics of spontaneous and read speech produced by a set of adolescent female talkers from Brooklyn, New York. Spontaneous speech was elicited by open-ended questions, while the Farm Script was used as the text for production of read speech at comfortable and at rapid rates. Overall, the rate of rapid read speech was correlated with the rate of comfortable spontaneous speech and comfortable reading, indicating a clear contribution of neuromuscular constraints to characteristic differences in speech rate. However, some talkers exhibiting the ability to produce rapid speech at the fastest rates adopted comfortable speaking rates at the slower end of the distribution. In light of these findings, we doubt that idiolectal differences in speaking rate can be accountable solely by appeal to differences between individuals in agility of oral articulators. [Work supported by NIH DC00308.]

This paper presents a novel architecture for keyword spotting in spontaneous speech, in which keyword model is trained from a small number of acoustic examples provided by a user. The word-spotting architecture relies on scoring patch feature vector sequences extracted by using sliding windows, and performing keyword-specific normalization and threshold setting. Dynamic time warping (DTW) based template matching and Gaussian Mixture Models (GMM) are proposed to model the keyword, and another GMM is proposed to model the non-keywords. Our keyword spotting experiments demonstrate the effectiveness of the proposed methods. More specifically, the proposed GMM log-likelihood ratio based method achieves about 17% absolute improvement in terms of recall rates compared to the baseline system.

The Acoustic Voice Quality Index (AVQI) is a widely adopted tool for assessing dysphonia, incorporating sustained vowel and continuous speech samples to enhance ecological validity. Despite its broad use, the reliability of AVQI measurements, particularly in digital health applications, remains underexplored. This study aims to review the literature on AVQI's development and validation from the perspective of internal consistency of acoustic measurements, and to assess the amount of speech required to reliably determine the AVQI of a voice recording. Two sub-studies are described. Study 1: A narrative review was conducted using Google Scholar and Scopus to identify studies mentioning “AVQI” and “reliability”. Key methodological details were extracted from studies reporting AVQI measurements, summarized, and discussed in terms of how the internal consistency of acoustic measurements was ensured across studies where AVQI had been validated or applied. Study 2: Recordings of read and spontaneous speech as well as sustained vowels produced by 54 native Swedish speakers (22 female, 32 male; age range: 46–78 years) were assessed in terms of the amount of speech required to obtain a reliable acoustic measurement of the speakers' voices. Simulations were performed using read and spontaneous speech materials of varying lengths. The variability in AVQI and its sub-measures was analyzed relative to the length (in words or in seconds) of continuous speech included. The result of study 1 shows that out of 129 identified studies, 85 reported on AVQI measurements. The review highlighted substantial variability in continuous speech lengths used across studies, ranging from 4–200 words. A recommendation of 3 s of voiced segments was often adhered to, but was found to lack sufficiently robust grounding. The simulations indicated that AVQI achieves internal consistency at speech lengths of approximately 50 words (or 20 s), which is longer than the current recommendation. Both read and spontaneous speech provided stable AVQI measurements at these speech lengths. AVQI thresholds obtained using speech lengths shorter than 50 words (20 s) may require re-evaluation. Robust standardization of continuous speech lengths is essential for the successful adoption of AVQI in digital health applications.

Huge quantities of ancient manuscripts are there in various National archives. Digitization of these manuscripts and historical documents is very important for making its access efficiently. Handwritten keyword spotting is very challenging task for Devanagari documents due to large variations in writing styles. Keyword spotting of unconstrained offline handwritten documents is performed based on matching scheme of word images. This paper presents an efficient keyword spotting approach for handwritten Devanagari documents. Experiments are conducted on historical datasets consisting of manuscripts by Oriental Research Institute @ Mysuru.

Keyword Spotting (KWS) in continuous speech is an emerging but challenging task that needs to deal with speech dynamics. Literature contains a variety of approaches for keyword spotting and spoken term detection. Most of these techniques are based on pattern based methods that are limited to a specific vocabulary of words with high computational cost for system training. A valuable contribution to the existing speaker dependent keyword spotting approaches is made in this paper by introducing a template matching based approach that exploits the Dempster's theory of Combined Evidence (CEv). The CEv plays a significant role as a Decision Support System (DSS) by integrating the keyword match/mismatch beliefs from multiple resources and providing a combined score (belief). Finally, performance of the proposed approach is compared with the existing keyword spotting techniques by using statistical analysis of the experimental results.

Support Vector Machine (SVM) may be defined as a machine learning algorithm that can be used for regression and classification. It is generally used for classification purposes. In this chapter, we will discuss Margin and Large Margin Methods and Kernel Methods. <br>