We evaluate some recent developments in recurrent neural network (RNN) based speech enhancement in the light of noise-robust automatic speech recognition (ASR). The proposed framework is based on Long Short-Term Memory (LSTM) RNNs which are discriminatively trained according to an optimal speech reconstruction objective. We demonstrate that LSTM speech enhancement, even when used ‘näıvely’ as f...

The problem of speech/music discrimination is a challenging research problem which significantly impacts Automatic Speech Recognition (ASR) performance. This paper proposes new features for the Speech/Music discrimination task. We propose to use a decomposition of the audio signal based on wavelets, which allows a good analysis of non stationary signal like speech or music. We compute different...

This paper explores the relationship between intelligibility and comprehensibility in speech synthesizers, and it designs an appropriate comprehension task for evaluating the speech synthesizers’ comprehensibility. Previous studies have predicted that a speech synthesizer with higher intelligibility will have higher performance in comprehension. Also, since the two most popular speech synthesis...

speaking assessment is still construed as a complicated, under-researched process from the vantage point of tasks and rater characteristics. the present study aimed at investigating if and how english major and none english major teachers differ in their perception of the construct of oral proficiency while assessing learners’ l2 oral proficiency.  to this end, 38 male and female non-native efl...

In this work, we present an approach for semantically based search for similar segments of a speech task, i.e., the search for audio segments in a row audio repository that are semantically related to the audio segment given by a user. Our approach is based on the lexical representation of segments of words that are enriched by semantic relations. We have studied different distance measures and...

the ph.d. entrance examinations of islamic azad university in iran are administered annually to select the best applicants for ph.d. programs. in consideration of the important decisions, which are made on the basis of the results of these examinations, the present study was conducted to provide a qualitative evaluation of field-specific language subtests (flss) of four entrance examinations ad...

few, if any, studies have investigated the effect of professional experience as a rater variable and type of assessment as a task variable on raters’ criteria in the assessment of speech acts. this study aimed to explore the impact of nonnative teachers’ professional experience on the use of criteria in monologic and dialogic assessment of 12 role-plays of 3 apology speech acts. to this end, 60...