SearchSkip to Search Results
- 2audio segmentation
- 2forced alignment
- 2speech recognition
- 2spoken word recognition
Measures of vowel overlap explore the acoustic similarity between proposed and existing vowel categories. They typically compare F1 and F2, and sometimes duration. In the present study, we investigate four methods of quantifying vowel overlap: the spectral overlap assessment metric (Wassink,...
The overlap of vowel categories is a fairly common linguistic phenomenon. But, it can be difficult to judge whether two supposedly distinct vowel categories have merged or not. One tool that a researcher may use is a quantification of the overlap based on acoustic properties of recorded vowel...
Poster for the paper "A comparison of input types to a deep neural network-based forced aligner," presented at Interspeech 2018. PAPER ABSTRACT: The present paper investigates the effect of different inputs on the accuracy of a forced alignment tool built using deep neural networks. Both raw...
The present paper investigates the effect of different inputs on the accuracy of a forced alignment tool built using deep neural networks. Both raw audio samples and Mel-frequency cepstral coefficients were compared as network inputs. A set of experiments were performed using the TIMIT speech...
How acoustic distinctiveness affects spoken word recognition: A pilot study
In the present study, I propose an acoustically-based alternative to phonological neighborhood density. Phonological neighborhood density has been used in many studies as an approximate quantification of lexical competition during spoken word recognition. However, phonological neighborhood...
A number of speech perception studies have been carried out to investigate how we process audio signals containing real words. However, comparatively fewer studies have been conducted looking at how listeners process audio signals containing phonotactically legal pseudowords. Some traditional...
Although most auditory lexical decision experiments are performed in a laboratory setting, humans tend to communicate in uncontrolled and noisy environments. We investigated, indirectly, the impact of noise and other distractions on lexical processing. The present study used a subset of words...
bBoiA sizable number of phonetic and psycholinguistic experiments have been conducted to investigate the recognition of real words. From this work, researchers have found that various characteristics of lexical items affect the recognition process, such as lexical frequency, phonotactic...