Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson’s Disease

The sophistication of artificial intelligence (AI) technologies has significantly advanced in the past decade. However, the observed unpredictability and variability of AI behavior in noisy signals is still underexplored and represents a challenge when trying to generalize AI behavior to real-life environments, especially for people with a speech disorder, who already experience reduced speech intelligibility. In the context of developing assistive technology for people with Parkinson's disease using automatic speech recognition (ASR), this pilot study reports on the performance of Google Cloud speech-to-text technology with dysarthric and healthy speech in the presence of multi-talker babble noise at different intensity levels. Despite sensitivities and shortcomings, it is possible to control the performance of these systems with current tools in order to measure speech intelligibility in real-life conditions.

Download Full-text

Empirical link between hypothesis diversity and fusion performance in an ensemble of automatic speech recognition systems

10.21437/interspeech.2013-672 ◽

2013 ◽

Author(s):

Kartik Audhkhasi ◽

Andreas M. Zavou ◽

Panayiotis G. Georgiou ◽

Shrikanth Narayanan

Keyword(s):

Speech Recognition ◽

Automatic Speech Recognition ◽

Recognition Systems

Download Full-text

Evaluation of Automatic Speech Recognition Systems

10.5753/sbbd.2021.17889 ◽

2021 ◽

Author(s):

Matheus Xavier Sampaio ◽

Regis Pires Magalhães ◽

Ticiana Linhares Coelho da Silva ◽

Lívia Almada Cruz ◽

Davi Romero de Vasconcelos ◽

...

Keyword(s):

Deep Learning ◽

Speech Recognition ◽

Automatic Speech Recognition ◽

Smart Homes ◽

The Other ◽

Learning Models ◽

Recognition Systems ◽

Microsoft Azure

Automatic Speech Recognition (ASR) is an essential task for many applications like automatic caption generation for videos, voice search, voice commands for smart homes, and chatbots. Due to the increasing popularity of these applications and the advances in deep learning models for transcribing speech into text, this work aims to evaluate the performance of commercial solutions for ASR that use deep learning models, such as Facebook Wit.ai, Microsoft Azure Speech, and Google Cloud Speech-to-Text. The results demonstrate that the evaluated solutions slightly differ. However, Microsoft Azure Speech outperformed the other analyzed APIs.

Download Full-text

Improving Aphasic Speech Recognition by Using Novel Semi-Supervised Learning Methods on AphasiaBank for English and Spanish

Applied Sciences ◽

10.3390/app11198872 ◽

2021 ◽

Vol 11 (19) ◽

pp. 8872

Author(s):

Iván G. Torre ◽

Mónica Romero ◽

Aitor Álvarez

Keyword(s):

Speech Recognition ◽

Supervised Learning ◽

Automatic Speech Recognition ◽

English Language ◽

Spanish Language ◽

Learning Methods ◽

Text Data ◽

Lower Performance ◽

Recognition Systems ◽

Fine Tune

Automatic speech recognition in patients with aphasia is a challenging task for which studies have been published in a few languages. Reasonably, the systems reported in the literature within this field show significantly lower performance than those focused on transcribing non-pathological clean speech. It is mainly due to the difficulty of recognizing a more unintelligible voice, as well as due to the scarcity of annotated aphasic data. This work is mainly focused on applying novel semi-supervised learning methods to the AphasiaBank dataset in order to deal with these two major issues, reporting improvements for the English language and providing the first benchmark for the Spanish language for which less than one hour of transcribed aphasic speech was used for training. In addition, the influence of reinforcing the training and decoding processes with out-of-domain acoustic and text data is described by using different strategies and configurations to fine-tune the hyperparameters and the final recognition systems. The interesting results obtained encourage extending this technological approach to other languages and scenarios where the scarcity of annotated data to train recognition models is a challenging reality.

Download Full-text

Feature Extraction Based on Speech Attractors in the Reconstructed Phase Space for Automatic Speech Recognition Systems

ETRI Journal ◽

10.4218/etrij.13.0112.0074 ◽

2013 ◽

Vol 35 (1) ◽

pp. 100-108 ◽

Cited By ~ 13

Author(s):

Yasser Shekofteh ◽

Farshad Almasganj

Keyword(s):

Feature Extraction ◽

Speech Recognition ◽

Phase Space ◽

Automatic Speech Recognition ◽

Reconstructed Phase Space ◽

Recognition Systems

Download Full-text

On the Application of Automated Software Testing Techniques to the Development and Maintenance of Speech Recognition Systems

Advanced Automated Software Testing ◽

10.4018/978-1-4666-0089-8.ch002 ◽

2012 ◽

pp. 30-48

Author(s):

Daniel Bolanos

Keyword(s):

Speech Recognition ◽

Software Testing ◽

Automatic Speech Recognition ◽

Automated Testing ◽

Automated Software Testing ◽

Testing Framework ◽

Methods And Techniques ◽

Testing Techniques ◽

Recognition Systems ◽

Automated Software

This chapter provides practitioners in the field with a set of guidelines to help them through the process of elaborating an adequate automated testing framework to competently test automatic speech recognition systems. Through this chapter the testing process of such a system is analyzed from different angles, and different methods and techniques are proposed that are well suited for this task.

Download Full-text