We present a novel study of relationships between automatic accent identification (AID) and accent-robust automatic speech recognition (ASR), using i-vector based AID and deep neural network, hidden Markov Model (DNN-HMM) based ASR. A visualization of the AID i-vector space and a novel analysis of the accent content of the WSJCAM0 corpus are presented. Accents that occur at the periphery of AID space

A deep neural network approach to voice conversion usually depends on a large amount of parallel training data from source and target speakers. In this paper, we propose a novel conversion pipeline, DeepConversion, that leverages a large amount of non-parallel, multi-speaker data, but requires only a small amount of parallel training data. It is believed that we can represent the shared characteristics

This paper presents a revised version of the Hearing-Aid Speech Perception Index (HASPI). The index is based on a model of the auditory periphery that incorporates changes due to hearing loss and is valid for both normal-hearing and hearing-impaired listeners. It is an intrusive metric that compares the time-frequency envelope and temporal fine structure (TFS) of a degraded signal to an unprocessed

Speech emotion recognition (SER) has recently been receiving increased interest due to the rapid advancements in affective computing and human computer interaction. English, German, Mandarin and Indian are among the most commonly considered languages for SER along with other European and Asian languages. However, few researches have implemented Arabic SER systems due to the scarcity of available Arabic

This paper presents a review of multi-objective deep learning methods that have been introduced in the literature for speech denoising. After stating an overview of conventional, single objective deep learning, and hybrid or combined conventional and deep learning methods, a review of the mathematical framework of the multi-objective deep learning methods for speech denoising is provided. A representative

Previous studies have suggested that female voices may impede verbal processing. For example, words were remembered less well and lexical decision was slower when spoken by a female speaker. The current study tried to replicate this gender effect in an auditory semantic/associative priming task that excluded any effects of speaker variability and extended previous research by examining the role of

This study investigates the relative contribution of L2 intonation, rhythm, and speech rate to L1 perceptions of accentedness and comprehensibility. The intonation, rhythm, and speech rate of an L1 speaker of Dutch was transferred onto the segmental string of four Spanish learners of Dutch, resulting in eight conditions that reflect all possible combinations of these prosodic cues. Our results show

In this paper, we investigate single-channel speech enhancement algorithms that operate in the short-time Fourier transform and take into account dependencies w.r.t. frequency. As a result of allowing for inter-frequency dependencies, the minimum mean square error optimal estimates of the short-time Fourier transform expansion coefficients are functions of complex-valued covariance matrices in general

Spoken documents, such as podcasts or lectures, are a growing presence in everyday life. Being able to automatically identify their discourse structure is an important step to understanding what a spoken document is about. Moreover, finer-grained units, such as paragraphs, are highly desirable for presenting and analyzing spoken content. However, little work has been done on discourse based speech

This paper builds on a multi-task Deep Neural Network (DNN), which provides an utterance-level feature representation called j-vector, to implement a Text-dependent Speaker Verification (TDSV) system. This technique exploits the speaker idiosyncrasies associated with individual pass-phrases. However, speaker information is known to be characteristic of more specific speech units and, thus, it is likely

The objectives of the dysarthria assessment are to discriminate dysarthric speech from normal speech, to estimate the severity of dysarthria in terms of the dysarthric speech intelligibility, and to find the motor speech subsystem which causes defects in speech production. In this work, analytic phase features are investigated for the objective assessment of dysarthria. In this connection, the importance

Many paralinguistic applications of speech demand the extraction of information about the speaker characteristics from as little speech data as possible. In this work, we explore the estimation of multiple physical parameters of the speaker from the short duration of speech in a multilingual setting. We explore different feature streams for age and body build estimation derived from the speech spectrum

This work presents a Kronecker product based methodology of frequency-domain beamforming of large sensor arrays for far-field broadband speech signals. The principal idea involves splitting up a given uniform linear array (ULA) into two smaller virtual ULAs (VULAs), using the Kronecker product. The linear system of the original ULA is bifurcated into two smaller linear systems of the VULAs. Henceforth

This paper presents a study of continuous word representations applied to automatic detection of speech recognition errors. A neural network architecture is proposed, which is well suited to handle continuous word representations, like word embeddings. We explore the use of several types of word representations: simple and combined linguistic embeddings, and acoustic ones associated to prosodic features

In linear predictive speech coders, the linear predictive coding (LPC) parameters are usually transformed into the line spectral frequency (LSF) representation for quantization. In this paper, the single and multiple frame coding of LSF parameters using deep neural network (DNN) and pyramid vector quanrizer (PVQ) are proposed. In the single-frame scheme, a non-linear DNN predictor which demonstrates

Speech emotion recognition plays an increasingly important role in emotional computing and is still a challenging task due to its complexity. In this study, we developed a framework integrating three distinctive classifiers: a deep neural network (DNN), a convolution neural network (CNN), and a recurrent neural network (RNN). The framework was used for categorical recognition of four discrete emotions

Deep learning has become one of the most widely accepted paradigms regarding machine learning. It focuses on the use of hierarchical data models and builds upon the notion that in order to learn about high level data representations, a better understanding of intermediate level representation is needed. Restricted Boltzmann Machines and deep belief networks are two main types of deep learning algorithms

Speech technology applications have emerged as a promising method for assessing speech-language abilities and at-home therapy, including prosody. Many applications assume that observed prosody errors are due to an underlying disorder; however, they may be instead due to atypical representations of prosody such as immature and developing speech motor control, or compensatory adaptations by those with

Human voice production for speech is an inefficient process in terms of energy expended to produce acoustic output. A traditional measure of vocal efficiency relates acoustic power radiated from the mouth to aerodynamic power produced in the trachea. This efficiency ranges between 0.001 % and 1.0 % in speech-like vocalization. Simplified Navier-Stokes equations for non-steady compressible airflow from

We introduce a new wavelet-based algorithm to enhance the quality of speech corrupted by multi-talker babble noise. The algorithm comprises three stages: The first stage classifies short frames of the noisy speech as speech-dominated or noise-dominated. We design this classifier specifically for multi-talker babble noise. The second stage performs preliminary de-nosing of noisy speech frames using

Matrix-styled sentence tests offer a closed-set paradigm that may be useful when evaluating speech intelligibility. Ideally, sentence test materials should reflect the distribution of phonemes within the target language. We developed and validated the Closed-set Mandarin Sentence (CMS) test to assess Mandarin speech intelligibility in noise. CMS test materials were selected to be familiar words and

The purpose of this study was to further develop a multi-tier model of the vocal tract area function in which the modulations of shape to produce speech are generated by the product of a vowel substrate and a consonant superposition function. The new approach consists of specifying input parameters for a target consonant as a set of directional changes in the resonance frequencies of the vowel substrate

Traditional studies of infant cry signals focus more on non-pathology-based classification of infants. In this paper, we introduce a noninvasive health care system that performs acoustic analysis of unclean noisy infant cry signals to extract and measure certain cry characteristics quantitatively and classify healthy and sick newborn infants according to only their cries. In the conduct of this newborn

An electrolarynx (EL) is a valuable rehabilitative option for individuals who have undergone laryngectomy, but current monotone ELs do not support controlled variations in fundamental frequency for producing tonal languages. The present study examined the production and perception of Mandarin Chinese using a customized hand-held EL driven by computer software to generate tonal distinctions (tonal EL)

Speech separation can be treated as a mask estimation problem, where interference-dominant portions are masked in a time-frequency representation of noisy speech. In supervised speech separation, a classifier is typically trained on a mixture set of speech and noise. It is important to efficiently utilize limited training data to make the classifier generalize well. When target speech is severely interfered

Children's speech presents a challenging problem for formant frequency measurement. In part, this is because high fundamental frequencies, typical of a children's speech production, generate widely spaced harmonic components that may undersample the spectral shape of the vocal tract transfer function. In addition, there is often a weakening of upper harmonic energy and a noise component due to glottal

Cognitive tests of verbal fluency (VF) consist of verbalizing as many words as possible in one minute that either start with a specific letter of the alphabet or belong to a specific semantic category. These tests are widely used in neurological, psychiatric, mental health, and school settings and their validity for clinical applications has been extensively demonstrated. However, VF tests are currently

Periodicity is an important property of speech signals. It is the basis of the signal's fundamental frequency and the pitch of voice, which is crucial to speech communication. This paper presents a novel framework of periodicity enhancement for noisy speech. The enhancement is applied to the linear prediction residual of speech. The residual signal goes through a constant-pitch time warping process

Previous studies have shown that "clear" speech, where the speaker intentionally tries to enunciate, has better intelligibility than "conversational" speech, which is produced in regular conversation. However, conversational and clear speech vary along a number of acoustic dimensions and it is unclear what aspects of clear speech lead to better intelligibility. Previously, Kain et al. [J. Acoust. Soc

A computationally efficient speech enhancement pipeline in noisy environments based on a single-processor implementation is developed for utilization in bilateral cochlear implant systems. A two-channel joint objective function is defined and a closed form solution is obtained based on the weighted-Euclidean distortion measure. The computational efficiency and no need for synchronization aspects of

We present and evaluate two statistical methods for estimating kinematic relationships of the speech production system: Artificial Neural Networks and Locally-Weighted Regression. The work is motivated by the need to characterize this motor system, with particular focus on estimating differential aspects of kinematics. Kinematic analysis will facilitate progress in a variety of areas, including the

Objective intelligibility measurement allows for reliable, low-cost, and repeatable assessment of innovative speech processing technologies, thus dispensing costly and time-consuming subjective tests. To date, existing objective measures have focused on normal hearing model, and limited use has been found for restorative hearing instruments such as cochlear implants (CIs). In this paper, we have evaluated

Most noise reduction algorithms rely on obtaining reliable estimates of the SNR of each frequency bin. For that reason, much work has been done in analyzing the behavior and performance of SNR estimation algorithms in the context of improving speech quality and reducing speech distortions (e.g., musical noise). Comparatively little work has been reported, however, regarding the analysis and investigation

Frequency lowering is a form of signal processing designed to deliver high-frequency speech cues to the residual hearing region of a listener with a high-frequency hearing loss. While this processing technique has been shown to improve the intelligibility of fricative and affricate consonants, perception of place of articulation has remained a challenge for hearing-impaired listeners, especially when

Few acoustic studies have attempted to examine anticipatory effects in the earliest part of the release of stop consonants. We investigated the ability of spectral coefficients to reveal anticipatory coarticulation in the burst and early aspiration of stops in monosyllables. Twenty American English speakers produced stop (/k,t,p/) - vowel (/æ,i,o/) - stop (/k,t,p/) sequences in two phrase positions

Linear predictive coding (LPC) analysis was used to create morphed natural tokens of English voiced stop consonants ranging from /b/ to /d/ and /d/ to /g/ in four vowel contexts (/i/, /æ/, /a/, /u/). Both vowel-consonant-vowel (VCV) and consonant-vowel (CV) stimuli were created. A total of 320 natural-sounding acoustic speech stimuli were created, comprising 16 stimulus series. A behavioral experiment

Designed to allow visual communication of speech signals, Cued Speech consists of discrete hand signals that are produced in synchrony with the visual mouth movements of speech. The purpose of this paper is to describe a method for transcribing these hand signals. Procedures are presented for identifying 1) the steady-state portion of the cue to be analyzed, 2) the cue's handshape, and 3) the cue's

Most of the existing intelligibility measures do not account for the distortions present in processed speech, such as those introduced by speech-enhancement algorithms. In the present study, we propose three new objective measures that can be used for prediction of intelligibility of processed (e.g., via an enhancement algorithm) speech in noisy conditions. All three measures use a critical-band spectral

This study aims at uncovering perceptually-relevant acoustic cues for the labial versus alveolar place of articulation distinction in syllable-initial plosives {/b/,/d/,/p/,/t/} and fricatives {/f/,/s/,/v/,/z/} in noise. Speech materials consisted of naturally-spoken consonant-vowel (CV) syllables from four talkers where the vowel was one of {/a/,/i/,/u/}. Acoustic analyses using logistic regression

The goal of the present study was to devise a means of representing languages in a perceptual similarity space based on their overall phonetic similarity. In Experiment 1, native English listeners performed a free classification task in which they grouped 17 diverse languages based on their perceived phonetic similarity. A similarity matrix of the grouping patterns was then submitted to clustering

The intelligibility of speech in noisy environments depends not only on the functionality of listeners' peripheral auditory systems, but also on cognitive factors such as their language learning experience. Previous studies have shown, for example, that normal-hearing listeners attending to a non-native language have more difficulty identifying speech targets in noisy conditions than do native listeners

A central question in spoken word recognition research is whether words are recognized relationally, in the context of other words in the mental lexicon [1, 2]. The current research evaluated metrics for measuring the influence of the mental lexicon on visually perceived (lipread) spoken word recognition. Lexical competition (the extent to which perceptually similar words influence recognition of a

The most common approaches to automatic emotion recognition rely on utterance level prosodic features. Recent studies have shown that utterance level statistics of segmental spectral features also contain rich information about expressivity and emotion. In our work we introduce a more fine-grained yet robust set of spectral features: statistics of Mel-Frequency Cepstral Coefficients computed over three

This paper briefly reviews current silent speech methodologies for normal and disabled individuals. Current techniques utilizing electromyographic (EMG) recordings of vocal tract movements are useful for physically healthy individuals but fail for tetraplegic individuals who do not have accurate voluntary control over the speech articulators. Alternative methods utilizing EMG from other body parts

Determining the location of phonemes is important to a number of speech applications, including training of automatic speech recognition systems, building text-to-speech systems, and research on human speech processing. Agreement of humans on the location of phonemes is, on average, 93.78% within 20 msec on a variety of corpora, and 93.49% within 20 msec on the TIMIT corpus. We describe a baseline

Assessment of prosody is important for diagnosis and remediation of speech and language disorders, for diagnosis of neurological conditions, and for foreign language instruction. Current assessment is largely auditory-perceptual, which has obvious drawbacks; however, automation of assessment faces numerous obstacles. We propose methods for automatically assessing production of lexical stress, focus

This work, which is couched in the theoretical framework of Articulatory Phonology, deals with the influence of speech rate on the change/variation from antepenultimate stress words into penultimate stress words in Brazilian Portuguese. Both acoustic and articulatory (EMMA) studies were conducted. On the acoustic side, results show different patterns of post-stressed vowel reduction according to the

Psychoacoustic experimentation shows that formant frequency shifts can give rise to more significant changes in phonetic vowel timber than differences in overall level, bandwidth, spectral tilt, and formant amplitudes. Carlson and Granström's perceptual and computational findings suggest that, in addition to spectral representations, the human ear uses temporal information on formant periodicities

It is widely known that language influences the way speech sounds are categorized. However, categorization of speech sounds by bilinguals is not well understood. There is evidence that bilinguals have different category boundaries than monolinguals, and there is evidence suggesting that bilinguals' phonemic boundaries can shift with language context. This phenomenon has been referred as the double

Learners of a second language practice their pronunciation by listening to and imitating utterances from native speakers. Recent research has shown that choosing a well-matched native speaker to imitate can have a positive impact on pronunciation training. Here we propose a voice-transformation technique that can be used to generate the (arguably) ideal voice to imitate: the own voice of the learner

The traditional power spectral subtraction algorithm is computationally simple to implement but suffers from musical noise distortion. In addition, the subtractive rules are based on incorrect assumptions about the cross terms being zero. A new geometric approach to spectral subtraction is proposed in the present paper that addresses these shortcomings of the spectral subtraction algorithm. A method

In this study, a method was developed to elicit three different speaking styles, reduced, citation, and hyperarticulated, using controlled sentence materials in a laboratory setting. In the first set of experiments, the reduced style was elicited by having twelve talkers read a sentence while carrying out a distractor task that involved recalling from short-term memory an individually-calibrated number

Making meaningful comparisons between the performance of the various speech enhancement algorithms proposed over the years, has been elusive due to lack of a common speech database, differences in the types of noise used and differences in the testing methodology. To facilitate such comparisons, we report on the development of a noisy speech corpus suitable for evaluation of speech enhancement algorithms

This paper focuses on optimal estimators of the magnitude spectrum for speech enhancement. We present an analytical solution for estimating in the MMSE sense the magnitude spectrum when the clean speech DFT coefficients are modeled by a Laplacian distribution and the noise DFT coefficients are modeled by a Gaussian distribution. Furthermore, we derive the MMSE estimator under speech presence uncertainty

Perceptual and acoustic research on dialect variation in the United States requires an appropriate corpus of spoken language materials. Existing speech corpora that include dialect variation are limited by poor recording quality, small numbers of talkers, and/or small samples of speech from each talker. The Nationwide Speech Project corpus was designed to contain a large amount of speech produced by

Perceptual systems in all modalities are predominantly sensitive to stimulus change, and many examples of perceptual systems responding to change can be portrayed as instances of enhancing contrast. Multiple findings from perception experiments serve as evidence for spectral contrast explaining fundamental aspects of perception of coarticulated speech, and these findings are consistent with a broad

Theoretical and practical motives alike have prompted recent investigations of multimodal speech perception. Theoretically, multimodal studies have extended the conceptualization of perceptual organization beyond the familiar modality-bound accounts deriving from Gestalt psychology. Practically, such investigations have been driven by a need to understand the proficiency of multimodal speech perception

This study used a multi-talker database containing intelligibility scores for 2000 sentences (20 talkers, 100 sentences), to identify talker-related correlates of speech intelligibility. We first investigated "global" talker characteristics (e.g., gender, F0 and speaking rate). Findings showed female talkers to be more intelligible as a group than male talkers. Additionally, we found a tendency for

This paper summarizes results from recent studies on the role of long-term memory in speech perception and spoken word recognition. Experiments on talker variability, speaking rate and perceptual learning provide strong evidence for implicit memory for very fine perceptual details of speech. Listeners apparently encode specific attributes of the talker's voice and speaking rate into long-term memory

This paper reports the results of three projects concerned with auditory word recognition and the structure of the lexicon. The first project was designed to experimentally test several specific predictions derived from MACS, a simulation model of the Cohort Theory of word recognition. Using a priming paradigm, evidence was obtained for acoustic-phonetic activation in word recognition in three experiments