Automatic speech recognition using articulatory features from subject-independent acoustic-to-articulatory inversion.
Ontology highlight
ABSTRACT:
SUBMITTER: Ghosh PK
PROVIDER: S-EPMC3189967 | biostudies-other | 2011 Oct
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Purpose: This research aimed to automatically predict intelligible speaking rate for individuals with Amyotrophic Lateral Sclerosis (ALS) based on speech acoustic and articulatory samples. Method: Twelve participants with ALS and two normal subjects produced a total of 1831 phrases. NDI Wave system was used to collect tongue and lip movement and acoustic data synchronously. A machine learning algorithm (i.e. support vector machine) was used to predict intelligible speaking rate (speech intelligibility?×?speaking rate) from acoustic and articulatory features of the recorded samples. Result: Acoustic, lip movement, and tongue movement information separately, yielded a R2 of 0.652, 0.660, and 0.678 and a Root Mean Squared Error (RMSE) of 41.096, 41.166, and 39.855 words per minute (WPM) between the predicted and actual values, respectively. Combining acoustic, lip and tongue information we obtained the highest R2 (0.712) and the lowest RMSE (37.562 WPM). Conclusion: The results revealed that our proposed analyses predicted the intelligible speaking rate of the participant with reasonably high accuracy by extracting the acoustic and/or articulatory features from one short speech sample. With further development, the analyses may be well-suited for clinical applications that require automatic speech severity prediction.
| S-EPMC6506394 | biostudies-literature
Project description:In this paper, a quantitative study of acoustic-to-articulatory inversion for vowel speech sounds by analysis-by-synthesis using the Maeda articulatory model is performed. For chain matrix calculation of vocal tract (VT) acoustics, the chain matrix derivatives with respect to area function are calculated and used in a quasi-Newton method for optimizing articulatory trajectories. The cost function includes a distance measure between natural and synthesized first three formants, and parameter regularization and continuity terms. Calibration of the Maeda model to two speakers, one male and one female, from the University of Wisconsin x-ray microbeam (XRMB) database, using a cost function, is discussed. Model adaptation includes scaling the overall VT and the pharyngeal region and modifying the outer VT outline using measured palate and pharyngeal traces. The inversion optimization is initialized by a fast search of an articulatory codebook, which was pruned using XRMB data to improve inversion results. Good agreement between estimated midsagittal VT outlines and measured XRMB tongue pellet positions was achieved for several vowels and diphthongs for the male speaker, with average pellet-VT outline distances around 0.15 cm, smooth articulatory trajectories, and less than 1% average error in the first three formants.
| S-EPMC3188964 | biostudies-other
Project description:The many-to-one mapping from representations in the speech articulatory space to acoustic space renders the associated acoustic-to-articulatory inverse mapping non-unique. Among various techniques, imposing smoothness constraints on the articulator trajectories is one of the common approaches to handle the non-uniqueness in the acoustic-to-articulatory inversion problem. This is because, articulators typically move smoothly during speech production. A standard smoothness constraint is to minimize the energy of the difference of the articulatory position sequence so that the articulator trajectory is smooth and low-pass in nature. Such a fixed definition of smoothness is not always realistic or adequate for all articulators because different articulators have different degrees of smoothness. In this paper, an optimization formulation is proposed for the inversion problem, which includes a generalized smoothness criterion. Under such generalized smoothness settings, the smoothness parameter can be chosen depending on the specific articulator in a data-driven fashion. In addition, this formulation allows estimation of articulatory positions recursively over time without any loss in performance. Experiments with the MOCHA TIMIT database show that the estimated articulator trajectories obtained using such a generalized smoothness criterion have lower RMS error and higher correlation with the actual measured trajectories compared to those obtained using a fixed smoothness constraint.
| S-EPMC2981125 | biostudies-other
Project description:Speech segmentation is a crucial step in automatic speech recognition because additional speech analyses are performed for each framed speech segment. Conventional segmentation techniques primarily segment speech using a fixed frame size for computational simplicity. However, this approach is insufficient for capturing the quasi-regular structure of speech, which causes substantial recognition failure in noisy environments. How does the brain handle quasi-regular structured speech and maintain high recognition performance under any circumstance? Recent neurophysiological studies have suggested that the phase of neuronal oscillations in the auditory cortex contributes to accurate speech recognition by guiding speech segmentation into smaller units at different timescales. A phase-locked relationship between neuronal oscillation and the speech envelope has recently been obtained, which suggests that the speech envelope provides a foundation for multi-timescale speech segmental information. In this study, we quantitatively investigated the role of the speech envelope as a potential temporal reference to segment speech using its instantaneous phase information. We evaluated the proposed approach by the achieved information gain and recognition performance in various noisy environments. The results indicate that the proposed segmentation scheme not only extracts more information from speech but also provides greater robustness in a recognition test.
| S-EPMC5120313 | biostudies-literature
Project description:PurposeAn image filter designed for reconstructing cerebrovascular trees from MR images is described. Current imaging techniques capture major cerebral vessels reliably, but often fail to detect small vessels, whose contrast is suppressed due to limited resolution, slow blood flow rate, and distortions around bifurcations or nonvascular structures. An incomplete view of angioarchitecture limits the information available to physicians.MethodsA novel Hessian-based filter for contrast-enhancement in MR angiography and venography for blood vessel reconstruction without introducing dangling segments is presented. We quantify filter performance with receiver-operating-characteristic and dice-similarity-coefficient analysis. Total extracted vascular length, number-of-segments, volume, surface-to-distance, and positional error are calculated for validation.ResultsReconstruction of cerebrovascular trees from MR images of six volunteers show that the new filter renders more complete representations of subject-specific cerebrovascular networks. Validation with phantom models shows the filter correctly detects blood vessels across all length scales without failing at bifurcations or distorting diameters.ConclusionThe novel filter can potentially improve the diagnosis of cerebrovascular diseases by delivering metrics and anatomy of the vasculature. It also facilitates the automated analysis of large datasets by computing biometrics free of operator subjectivity. The high quality reconstruction enables computational mesh generation for subject-specific hemodynamic simulations. Magn Reson Med 77:398-410, 2017. © 2016 Wiley Periodicals, Inc.
| S-EPMC4947568 | biostudies-literature
Project description:Automatic speech recognition (ASR) has been an active area of research. Training with large annotated datasets is the key to the development of robust ASR systems. However, most available datasets are focused on high-resource languages like English, leaving a significant gap for low-resource languages. Among these languages is Punjabi, despite its large number of speakers, Punjabi lacks high-quality annotated datasets for accurate speech recognition. To address this gap, we introduce three labeled Punjabi speech datasets: Punjabi Speech (real speech dataset) and Google-synth/CMU-synth (synthesized speech datasets). The Punjabi Speech dataset consists of read speech recordings captured in various environments, including both studio and open settings. In addition, the Google-synth dataset is synthesized using Google's Punjabi text-to-speech cloud services. Furthermore, the CMU-synth dataset is created using the Clustergen model available in the Festival speech synthesis system developed by CMU. These datasets aim to facilitate the development of accurate Punjabi speech recognition systems, bridging the resource gap for this important language.
| S-EPMC10749247 | biostudies-literature
Project description:Accurate transcription of audio recordings in psychotherapy would improve therapy effectiveness, clinician training, and safety monitoring. Although automatic speech recognition software is commercially available, its accuracy in mental health settings has not been well described. It is unclear which metrics and thresholds are appropriate for different clinical use cases, which may range from population descriptions to individual safety monitoring. Here we show that automatic speech recognition is feasible in psychotherapy, but further improvements in accuracy are needed before widespread use. Our HIPAA-compliant automatic speech recognition system demonstrated a transcription word error rate of 25%. For depression-related utterances, sensitivity was 80% and positive predictive value was 83%. For clinician-identified harm-related sentences, the word error rate was 34%. These results suggest that automatic speech recognition may support understanding of language patterns and subgroup variation in existing treatments but may not be ready for individual-level safety surveillance.
| S-EPMC7270106 | biostudies-literature
Project description:BackgroundThere are no reliable and validated objective biomarkers for the assessment of depression severity. We aimed to investigate the association between depression severity and timing-related speech features using speech recognition technology.MethodPatients with major depressive disorder (MDD), those with bipolar disorder (BP), and healthy controls (HC) were asked to engage in a non-structured interview with research psychologists. Using automated speech recognition technology, we measured three timing-related speech features: speech rate, pause time, and response time. The severity of depression was assessed using the Hamilton Depression Rating Scale 17-item version (HAMD-17). We conducted the current study to answer the following questions: 1) Are there differences in speech features among MDD, BP, and HC? 2) Do speech features correlate with depression severity? 3) Do changes in speech features correlate with within-subject changes in depression severity?ResultsWe collected 1058 data sets from 241 individuals for the study (97 MDD, 68 BP, and 76 HC). There were significant differences in speech features among groups; depressed patients showed slower speech rate, longer pause time, and longer response time than HC. All timing-related speech features showed significant associations with HAMD-17 total scores. Longitudinal changes in speech rate correlated with changes in HAMD-17 total scores.ConclusionsDepressed individuals showed longer response time, longer pause time, and slower speech rate than healthy individuals, all of which were suggestive of psychomotor retardation. Our study suggests that speech features could be used as objective biomarkers for the assessment of depression severity.
| S-EPMC7485753 | biostudies-literature
Project description:Acoustic holograms are the keystone of modern acoustics. They encode three-dimensional acoustic fields in two dimensions, and their quality determines the performance of acoustic systems. Optimisation methods that control only the phase of an acoustic wave are considered inferior to methods that control both the amplitude and phase of the wave. In this paper, we present Diff-PAT, an acoustic hologram optimisation platform with automatic differentiation. We show that in the most fundamental case of optimizing the output amplitude to match the target amplitude; our method with only phase modulation achieves better performance than conventional algorithm with both amplitude and phase modulation. The performance of Diff-PAT was evaluated by randomly generating 1000 sets of up to 32 control points for single-sided arrays and single-axis arrays. This optimisation platform for acoustic hologram can be used in a wide range of applications of PATs without introducing any changes to existing systems that control the PATs. In addition, we applied Diff-PAT to a phase plate and achieved an increase of > 8 dB in the peak noise-to-signal ratio of the acoustic hologram.
| S-EPMC8209099 | biostudies-literature
Project description:Emerging neurophysiologic evidence indicates that motor systems are activated during the perception of speech, but whether this activity reflects basic processes underlying speech perception remains a matter of considerable debate. Our contribution to this debate is to report direct behavioral evidence that specific articulatory commands are activated automatically and involuntarily during speech perception. We used electropalatography to measure whether motor information activated from spoken distractors would yield specific distortions on the articulation of printed target syllables. Participants produced target syllables beginning with /k/ or /s/ while listening to the same syllables or to incongruent rhyming syllables beginning with /t/. Tongue-palate contact for target productions was measured during the articulatory closure of /k/ and during the frication of /s/. Results revealed "traces" of the incongruent distractors on target productions, with the incongruent /t/-initial distractors inducing greater alveolar contact in the articulation of /k/ and /s/ than the congruent distractors. Two further experiments established that (i) the nature of this interference effect is dependent specifically on the articulatory properties of the spoken distractors; and (ii) this interference effect is unique to spoken distractors and does not arise when distractors are presented in printed form. Results are discussed in terms of a broader emerging framework concerning the relationship between perception and action, whereby the perception of action entails activation of the motor system.
| S-EPMC2818927 | biostudies-literature