This paper describes LUCID, the London UCL Clear Speech in Interaction Database, which contains spontaneous and read speech in clear and casual speaking styles for 40 Southern British English speakers. The problem-solving task used to collect the spontaneous speech, the DiapixUK task, is also described, along with ways of using the task to elicit different types of clear speech without explicit...

In the Spring of 2012, fans of the Gonzaga University basketball team used hate speech on social media site Twitter to express their frustration at losing a game to the Brigham Young University team. In response, the students in the Hate Studies in Business course started a student-led movement to “Take the Hate Out of Hoops.” The students applied their lessons in virtue ethics and leveraged th...

In the speech technology research community there is an increasing trend to use open source solutions. We present a new tool in that spirit, WaveSurfer, which has been developed at the Centre for Speech Technology at KTH. It has been designed for tasks such as viewing, editing, and labeling of audio data. WaveSurfer is built around a small core to which most functionality is added in the form o...

Experimental evidence about human speech processing and linguistic memory shows that words are not spelled from letter-like units, whether thought of as phones or phonemes. Linguists, like others with a Western education and a lifetime of literacy, identify speech quite automatically with a sequence of letter-sized units. Consonants and vowels seem like directly observable units in speech. Howe...

In this paper, we report the 2015 community-based Signal Separation Evaluation Campaign (SiSEC 2015). This SiSEC consists of four speech and music datasets including two new datasets: “Professionally produced music recordings” and “Asynchronous recordings of speech mixtures”. Focusing on them, we overview the campaign specifications such as the tasks, datasets and evaluation criteria. We also s...

This paper describes the “Speech Recognition Virtual Kitchen” environment which has the goals to promote community sharing of research techniques, foster innovative experimentation, and provide solid reference systems as a tool for education, research, and evaluation with a focus on, but not restricted to, speech and language research. The core of the research infrastructure is the use of Virtu...

In this article, we propose a web based listening test system that can be used with a large range of listeners. Our main goals were to make the configuration of the tests as simple and flexible as possible, to simplify the recruiting of the testees and, of course, to keep track of the results using a relational database. This first version of our system can perform the most widely used listenin...

This paper describes recent developments in the Speech Recognition Virtual Kitchen. The core of the research infrastructure is the use of Virtual Machines or Linux containers. We liken these to a “kitchen”, because they provide “appliances” (e.g., speech recognition tool-kits), “recipes” (scripts for creating state-ofthe art systems), and “ingredients” (language data). Users can now download a ...

Ageing is part of the normal evolution of human beings. Demographic projections to 2030 indicate that more than 60 countries will have at least 2 million people age 65 or older. Yet knowlegde about speech in the elderly is still dispersed and incomplete, in particular in the area of normal ageing. Prosody within a linguistic community is triggered by a number of parameters which are investigate...

Continuous speech recognition research activities within the DARPA Spoken Language community have, within the past several years, been focussed on the Resource Management (RM) and Air Travel Information System (ATIS) corpora. Within the past year, plans have been developed for a large, multi-component "general-purpose English, large vocabulary, natural language, high perplexity corpus" known as...