Aculab collaborates with the University of York for language and linguistic science project

Automatic speaker recognition (ASR) is increasingly used by commercial institutions to identify individuals from their voices, and by forensic labs for voice evidence in legal cases. Despite their very low error rates in experiments, little is known about what information is actually captured by state-of-the art ASR systems. This collaborative project, involving Aculab and the University of York, will examine how speaker-characterising information captured by ASR systems maps on to linguistic properties of the voice. This study has important implications for the development and improvement of ASR, enhancing public and legal/judicial understanding of ASR, and improving voice analysis in forensic cases.

Understanding and modelling the human voice in all its complexity is a key issue in both the humanities (linguistics, phonetics) and the sciences (engineering, computer science). Different disciplines approach this problem in fundamentally different ways. Despite the clear overlap in interests, very little work has been situated at the intersection between linguistics and speech technology.

The project will contribute to the small but emerging body of research investigating how linguistic information can help us better understand ASR systems. The project will address three key questions:

1.     To what extent do ASR systems capture tangible linguistic properties of a voice?

2.     By understanding what information is captured by ASR systems, can we predict which speakers will be problematic for the system?

3.     Can linguistic information be used to improve the performance of ASR?

“The collaboration between York and Aculab is unique,” stated Dr Vincent Hughes, Department of Language and Linguistic Science, at the University of York, “and we are very pleased to work with a leading commercial developer of ASR systems,” he continued.

“York is home to a world leading research centre for forensic speech science, and the project represents one of the only large-scale investigations into how speaker-specific information is encoded in the voice,” elaborated Dr Hughes.

“We will be delighted to host the successful student and to provide unique employment-related skills via experience in a commercial environment,” explained Dr Ladan Baghai-Ravary, Speech Technology Director at Aculab.

Dr Baghai-Ravary went on to add, “This collaborative project will allow us to address new forensic applications of our technology, and in general it will increase the uptake of automatic speech and voice analysis within the forensics industry, by providing a legally acceptable interpretation and justification of the evidence that such systems can give.”

VoiSentry is highly scalable, supportive of multi-factor authentication, and offers innovative resilience and database features. Interaction with Aculab’s system is via the VoiSentry API, which facilitates ready integration with any IVR, self-service, or contact centre solution. To explore the system, click here or for any further information, contact Aculab.

Details about the project, including eligibility criteria and how to apply can be found here:

https://docs.google.com/document/d/1UIz-IyFcCelcU0yQlX6Ck_wO_L3TCxLIIdHZ7o8iV0k/edit#

Potential applicants are asked to contact Dr Hughes (This email address is being protected from spambots. You need JavaScript enabled to view it.) to express their interest before applying for the position'?

The WRoCAH web pages detailing the scheme can be viewed here: http://wrocah.ac.uk/new-student/2019-cda/

About Aculab

Aculab offers its VoiSentry speaker verification system to facilitate an intuitive and convenient user experience, enhanced fraud security, and time/cost savings compared to manual authentication methods.

Additionally, Aculab offers a wide range of APIs to serve the evolving needs of automated and interactive applications, whether on-premise, data center hosted, or cloud-based. It’s telecoms related APIs include voice, data, fax, speech and SMS, on hardware, software and cloud-based platforms, giving users the choice between capital investment and cost-effective, ‘pay as you go’ alternatives.

Many years of experience in helping to drive its customers’ success has led to over 1000 customers, in more than 80 countries worldwide, including developers, integrators and service providers, adopting Aculab’s technology for a wide variety of business-critical services and solutions.

Aculab has an office in the USA and its head office is located in Milton Keynes, UK.

Written on 06 November 2018.