Interspeech最新文献

Magnetic Resonance Imaging (MRI) allows analyzing speech production by capturing high-resolution images of the dynamic processes in the vocal tract. In clinical applications, combining MRI with synchronized speech recordings leads to improved patient outcomes, especially if a phonological-based approach is used for assessment. However, when audio signals are unavailable, the recognition accuracy of sounds is decreased when using only MRI data. We propose a contrastive learning approach to improve the detection of phonological classes from MRI data when acoustic signals are not available at inference time. We demonstrate that frame-wise recognition of phonological classes improves from an f1 of 0.74 to 0.85 when the contrastive loss approach is implemented. Furthermore, we show the utility of our approach in the clinical application of using such phonological classes to assess speech disorders in patients with tongue cancer, yielding promising results in the recognition task.

Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with spontaneous voice assistant (VA) commands from 35 older adults in a controlled setting. Specifically, a command-generation task is designed with pre-defined intents for participants to freely generate commands that are more associated with cognitive ability than read commands. We develop MCI classification and regression models with audio, textual, intent, and multimodal fusion features. We find the command-generation task outperforms the command-reading task with an average classification accuracy of 82%, achieved by leveraging multimodal fusion features. In addition, generated commands correlate more strongly with memory and attention subdomains than read commands. Our results confirm the effectiveness of the command-generation task and imply the promise of using longitudinal in-home commands for MCI detection.

Speech foundation models are remarkably successful in various consumer applications, prompting their extension to clinical use-cases. This is challenged by small clinical datasets, which precludes effective fine-tuning. We tested the efficacy of two models to classify participants by segmental (Wav2Vec2.0) and suprasegmental (Trillsson) speech analysis windows. Analysis at both time scales has shown differences in the context of cognitive decline. Speakers were classified as healthy controls (HC), Amyloid-β+ (Aβ+), mild cognitive impairment (MCI), or dementia. A subset of W2V2 and Trillsson representations showed large effect size between HC and each risk factor. Cross-validation showed W2V2 consistently outperforms Trillsson. Mean macro-F1 of 54.1%, 63.5%, and 72.0% in were found for classifying Aβ+, MCI, and dementia from HC. Repeatability of Trillsson and W2V2 showed intraclass correlations of 0.30 and 0.41. Reliability of such models must be enhanced for clinical speech analysis and longitudinal tracking.

Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems [1, 2] which lack efficiency and robustness, and are sensitive to template design. In this paper, we propose YOLO-Stutter: a first end-to-end method that detects dysfluencies in a time-accurate manner. YOLO-Stutter takes imperfect speech-text alignment as input, followed by a spatial feature aggregator, and a temporal dependency extractor to perform region-wise boundary and class predictions. We also introduce two dysfluency corpus, VCTK-Stutter and VCTK-TTS, that simulate natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation. Our end-to-end method achieves state-of-the-art performance with a minimum number of trainable parameters for on both simulated data and real aphasia speech. Code and datasets are open-sourced at https://github.com/rorizzz/YOLO-Stutter.

Automated goodness of pronunciation scores measure deviation from typical adult speech by first phonetically segmenting speech using forced alignment and then computing phoneme likelihoods. Care must be taken to distinguish between the impact of alignment error (a spurious signal) and true acoustic deviation on the automated score. Using mixed effects modeling, we predict $\Delta PLLR$ , the difference between pronunciation scores computed using manual alignment ( $PLL{R}_m$ ) versus computed using automatic forced alignments ( $PLL{R}_a$ ). Pronunciation deviations and alignment error are both magnified in children's speech and may be influenced by factors such as phoneme position and phoneme type. Our methodology shows that alignment error has a moderate effect on $\Delta PLLR$ , and other variables have small to no effect. Manual $\mathrm{PLLR}$ closely matches automatically calculated $\mathrm{PLLR}$ following cross utterance averaging. Thus, practical comparisons between child speakers should be very comparable across the two methods.

The most common types of voice disorders are associated with hyperfunctional voice use in daily life. Although current clinical practice uses measures from brief laboratory recordings to assess vocal function, it is unclear how these relate to an individual's habitual voice use. The purpose of this study was to quantify the correlation and offset between voice features computed from laboratory and ambulatory recordings in speakers with and without vocal hyperfunction. Features derived from a neck-surface accelerometer included estimates of sound pressure level, fundamental frequency, cepstral peak prominence, and spectral tilt. Whereas some measures from laboratory recordings correlated significantly with those captured during daily life, only approximately 6-52% of the actual variance was accounted for. Thus, brief voice assessments are quite limited in the extent to which they can accurately characterize the daily voice use of speakers with and without vocal hyperfunction.

We investigate the feasibility, task compliance and audiovisual data quality of a multimodal dialog-based solution for remote assessment of Amyotrophic Lateral Sclerosis (ALS). 53 people with ALS and 52 healthy controls interacted with Tina, a cloud-based conversational agent, in performing speech tasks designed to probe various aspects of motor speech function while their audio and video was recorded. We rated a total of 250 recordings for audio/video quality and participant task compliance, along with the relative frequency of different issues observed. We observed excellent compliance (98%) and audio (95.2%) and visual quality rates (84.8%), resulting in an overall yield of 80.8% recordings that were both compliant and of high quality. Furthermore, recording quality and compliance were not affected by level of speech severity and did not differ significantly across end devices. These findings support the utility of dialog systems for remote monitoring of speech in ALS.