Adam C. Lammert

Adam C. Lammert

Auto-generated profile, based on publicly available information

Adam C. Lammert

Mathematics and Computer Science Department, College of the Holy Cross, Worcester, MA, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 February 2022 in Perspectives of the Asha Special Interest Groups
Verified
Journal Article
Closed access
VRVikram Ramanarayanan
Vikram Ramanarayanan
ALAdam C. Lammert
Adam C. Lammert
HRHannah Rowe
Hannah Rowe
TQThomas F. Quatieri
Thomas F. Quatieri
JGJordan R. Green
Jordan R. Green
Purpose: Over the past decade, the signal processing and machine learning literature has demonstrated notable advancements in automated speech processing with the use of artificial intelligence for medical assessment and monitoring (e.g., depression, dementia, and Parkinson's disease, among others). Meanwhile, the clinical speech literature has identified several interpretable, theoretically motivated measures that are sensitive to abnormalities in the cognitive, linguistic, affective, motoric, and anatomical domains. Both fields have, thus, independently demonstrated the potential for speech to serve as an informative biomarker for detecting different psychiatric and physiological conditions. However, despite these parallel advancements, automated speech biomarkers have not been integrated into routine clinical practice to date. Conclusions: In this article, we present opportunities and challenges for adoption of speech as a biomarker in clinical practice and research. Toward clinical acceptance and adoption of speech-based digital biomarkers, we argue for the importance of several factors such as robustness, specificity, diversity, and physiological interpretability of speech analytics in clinical applications.

1 March 2016 in Computer Speech & Language
Verified
Journal Article
Open access
MLMing Li
Ming Li
JKJangwon Kim
Jangwon Kim
ALAdam Lammert
Adam Lammert
PGPrasanta Kumar Ghosh
Prasanta Kumar Ghosh
VRVikram Ramanarayanan
Vikram Ramanarayanan
SNShrikanth Narayanan
Shrikanth Narayanan
We propose a practical, feature-level and score-level fusion approach by combining acoustic and estimated articulatory information for both text independent and text dependent speaker verification. From a practical point of view, we study how to improve speaker verification performance by combining dynamic articulatory information with the conventional acoustic features. On text independent speaker verification, we find that concatenating articulatory features obtained from measured speech production data with conventional Mel-frequency cepstral coefficients (MFCCs) improves the performance dramatically. However, since directly measuring articulatory data is not feasible in many real world applications, we also experiment with estimated articulatory features obtained through acoustic-to-articulatory inversion. We explore both feature level and score level fusion methods and find that the overall system performance is significantly enhanced even with estimated articulatory features. Such a performance boost could be due to the inter-speaker variation information embedded in the estimated articulatory features. Since the dynamics of articulation contain important information, we included inverted articulatory trajectories in text dependent speaker verification. We demonstrate that the articulatory constraints introduced by inverted articulatory features help to reject wrong password trials and improve the performance after score level fusion. We evaluate the proposed methods on the X-ray Microbeam database and the RSR 2015 database, respectively, for the aforementioned two tasks. Experimental results show that we achieve more than 15% relative equal error rate reduction for both speaker verification tasks.


4 November 2021 in Journal of Speech, Language, and Hearing Research
Verified
Journal Article
Closed access
HRHannah Rowe
Hannah Rowe
KSKaila L. Stipancic
Kaila L. Stipancic
ALAdam C. Lammert
Adam C. Lammert
JGJordan R. Green
Jordan R. Green
Purpose: This study investigated the criterion (analytical and clinical) and construct (divergent) validity of a novel, acoustic-based framework composed of five key components of motor control: Coordination, Consistency, Speed, Precision, and Rate. Method: Acoustic and kinematic analyses were performed on audio recordings from 22 subjects with amyotrophic lateral sclerosis during a sequential motion rate task. Perceptual analyses were completed by two licensed speech-language pathologists, who rated each subject's speech on the five framework components and their overall severity. Analytical and clinical validity were assessed by comparing performance on the acoustic features to their kinematic correlates and to clinician ratings of the five components, respectively. Divergent validity of the acoustic-based framework was then assessed by comparing performance on each pair of acoustic features to determine whether the features represent distinct articulatory constructs. Bivariate correlations and partial correlations with severity as a covariate were conducted for each comparison. Results: Results revealed moderate-to-strong analytical validity for every acoustic feature, both with and without controlling for severity, and moderate-to-strong clinical validity for all acoustic features except Coordination, without controlling for severity. When severity was included as a covariate, the strong associations for Speed and Precision became weak. Divergent validity was supported by weak-to-moderate pairwise associations between all acoustic features except Speed (second-formant [F2] slope of consonant transition) and Precision (between-consonant variability in F2 slope). Conclusions: This study demonstrated that the acoustic-based framework has potential as an objective, valid, and clinically useful tool for profiling articulatory deficits in individuals with speech motor disorders. The findings also suggest that compared to clinician ratings, instrumental measures are more sensitive to subtle differences in articulatory function. With further research, this framework could provide more accurate and reliable characterizations of articulatory impairment, which may eventually increase clinical confidence in the diagnosis and treatment of patients with different articulatory phenotypes.

15 March 2022 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ADApiwat Ditthapron
Apiwat Ditthapron
ALAdam C. Lammert
Adam C. Lammert
EAEmmanuel Agu
Emmanuel Agu
Traumatic Brain Injury (TBI) is caused by a head injury that affects the brain, impairing cognitive and communication function and resulting in speech and language disorders. Over 80,000 individuals in the US suffer from long-term TBI disabilities and continuous monitoring after TBI is essential to facilitate rehabilitation and prevent regression. Prior work has demonstrated the feasibility of TBI monitoring from speech by leveraging advancements in Artificial Intelligence (AI) and speech processing technology. However, much of prior work explored TBI detection using scripted speech tasks such as diadochokinesis tests or reading a passage. Such scripted approaches require active user involvement that significantly burdens participants. Moreover, they are episodic, are not realistic, and do not provide a longitudinal picture of the user's TBI condition. This study proposes a continuous TBI monitoring from changes in acoustic features of spontaneous speech collected passively using the smartphone. Low-level acoustic features are extracted using parametrized Sinc filters (pSinc) that are then classified TBI (yes/no) using a cascading Gated Recurrent Unit (cGRU). The cGRU model utilizes a cell gate unit in the GRU to store and incorporate each individual's prediction history as prior knowledge into the model. In rigorous evaluation, our proposed method outperformed prior TBI classification methods on conversational speech recorded during patient-therapist discourses following TBI, achieving 83.87% balanced accuracy. Furthermore, unique words that are important in TBI prediction were identified using SHapley Additive exPlanations (SHAP). A correlation was also found between features acquired by the proposed method and coordination deficits following TBI.

18 May 2023 in IEEE Open Journal of Engineering in Medicine and Biology
Verified
Journal Article
Open access
AHAlec Hoyland
Alec Hoyland
NBNelson V. Barnett
Nelson V. Barnett
BRBenjamin W. Roop
Benjamin W. Roop
DADanae Alexandrou
Danae Alexandrou
MCMyah Caplan
Myah Caplan
ALAdam C. Lammert
Adam C. Lammert
Goal: This study validates an approach to characterizing the sounds experienced by tinnitus patients via reverse correlation, with potential for characterizing a wider range of sounds than currently possible. Methods: Ten normal-hearing subjects assessed the subjective similarity of random auditory stimuli and target tinnitus-like sounds (“buzzing” and “roaring”). Reconstructions of the targets were obtained by regressing subject responses on the stimuli, and were compared for accuracy to the frequency spectra of the targets using Pearson's $r$ . Results: Reconstruction accuracy was significantly higher than chance across subjects: buzzing: $0.52 \pm 0.27$ (mean $\pm$ s.d.), $t(9) = 5.766$ , $p < 0.001$ ; roaring: $0.62 \pm 0.23$ , $t(9) = 5.76$ , $p < 0.001$ ; combined: $0.57 \pm 0.25$ , $t(19) = 7.542$ , $p < 0.001$ . Conclusion: Reverse correlation can accurately reconstruct non-tonal tinnitus-like sounds in normal-hearing subjects, indicating its potential for characterizing the sounds experienced by patients with non-tonal tinnitus.