Search

Listeners track distributions of speech sounds along percep-tual dimensions. We introduce a method for evaluating hy-potheses about what those dimensions are, using a cognitivemodel whose prior distribution is estimated directly from speechrecordings. We use this method to evaluate two speaker nor-malization algorithms against human data. Simulations showthat representations that are normalized across speakers predicthuman discrimination data better than unnormalized representa-tions, consistent with previous research. Results further revealdifferences across normalization methods in how well eachpredicts human data. This work provides a framework forevaluating hypothesized representations of speech and lays thegroundwork for testing models of speech perception on naturalspeech recordings from ecologically valid settings.

This paper reports on the results of the Zero Resource Speech Challenge 2015, the first unified benchmark for zero resource speech technology, which aims at the unsupervised discovery of subword and word units from raw speech. This paper discusses the motivation for the challenge, its data sets, tasks and baseline systems. We outline the ideas behind the systems that were submitted for the two challenge tracks: unsupervised subword unit modeling and spoken term discovery, and summarize their results. The results obtained by participating teams show great promise; many systems beat the provided baselines and some even perform better than comparable supervised systems. [ABSTRACT FROM AUTHOR]

We investigate the hypothesis that the linguistic content underlying human speech may be coded in the pattern of timings of various acoustic "events" (landmarks) in the speech signal. This hypothesis is supported by several strands of research in the fields of linguistics, speech perception, and neuroscience. In this paper, we put these scientific motivations to the test by formulating a point process-based computational framework for the task of spotting keywords in continuous speech. We find that even with a noisy and extremely sparse phonetic landmark-based point process representation, keywords can be spotted with accuracy levels comparable to recently studied hidden Markov model-based keyword spotting systems. We show that the performance of our keyword spotting system in the high-precision regime is better predicted by the median duration of the keyword rather than simply the number of its constituent syllables or phonemes. When we are confronted with very few (in the extreme case, zero) examples of the keyword in question, we find that constructing a keyword detector from its component syllable detectors provides a viable approach. [ABSTRACT FROM AUTHOR]

This paper elaborates on a computational model for speech recognition that is inspired by several interrelated strands of research in phonology, acoustic phonetics, speech perception, and neuroscience. The goals are twofold: (i) to explore frameworks for recognition that may provide a viable alternative to the current hidden Markov model (HMM) based speech recognition systems and (ii) to provide a computational platform that will facilitate engaging, quantifying, and testing various theories in the scientific traditions in phonetics, psychology, and neuroscience. This motivation leads to an approach that constructs a hierarchically structured point process representation based on distinctive feature landmark detectors and probabilistically integrates the firing patterns of these detectors to decode a phonological sequence. The accuracy of a broad class recognizer based on this framework is competitive with equivalent HMM-based systems. Various avenues for future development of the presented methodology are outlined. [ABSTRACT FROM AUTHOR]