Related papers: A Perceptual Alphabet for the 10-dimensional Phone…
Let $A$ be an alphabet and $SP^\diamond(A)$ denote the class of all countable N-free partially ordered sets labeled by $A$, in which chains are scattered linear orderings and antichains are finite. We characterize the rational languages of…
Prominences and boundaries are the essential constituents of prosodic structure in speech. They provide for means to chunk the speech stream into linguistically relevant units by providing them with relative saliences and demarcating them…
Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these…
This paper describes the LIA speaker recognition system developed for the Speaker Recognition Evaluation (SRE) campaign. Eight sub-systems are developed, all based on a state-of-the-art approach: i-vector/PLDA which represents the…
Loudspeaker-based spatial audio reproduction schemes are increasingly used for evaluating hearing aids in complex acoustic conditions. To further establish the feasibility of this approach, this study investigated the interaction between…
The complexity of a system description is a function of the entropy of its symbolic description. Prior to computing the entropy of the system description, an observation scale has to be assumed. In natural language texts, typical scales are…
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and…
Deaf or hard-of-hearing (DHH) speakers typically have atypical speech caused by deafness. With the growing support of speech-based devices and software applications, more work needs to be done to make these devices inclusive to everyone. To…
Building a diagnosis model for primary progressive aphasia (PPA) has been challenging due to the data scarcity. Collecting clinical data at scale is limited by the high vulnerability of clinical population and the high cost of expert…
This paper introduces Linguistic Style Improvisation, a theory and set of algorithms for improvisation of spoken utterances by artificial agents, with applications to interactive story and dialogue systems. We argue that linguistic style is…
Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to…
Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…
Diagnostic procedures for ASD (autism spectrum disorder) involve semi-naturalistic interactions between the child and a clinician. Computational methods to analyze these sessions require an end-to-end speech and language processing pipeline…
Speech modeling methods learn one embedding for a fixed segment of speech, typically in between 10-25 ms. The information present in speech can be divided into two categories: "what is being said" (content) and "how it is expressed" (other)…
Dysphasic subjects do not have complete linguistic abilities and only produce a weakly structured, topicalized language. They are offered artificial symbolic languages to help them communicate in a way more adapted to their linguistic…
Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…
In this work, we propose a deep beamforming framework for speech enhancement in dynamic acoustic environments. The framework learns time-varying beamformer weights from noisy multichannel signals via a deep neural network, guided by a…
We present a model of speech perception which takes into account effects of correlations between sounds. Words in this model correspond to the attractors of a suitably chosen descent dynamics. The resulting lexicon is rich in short words,…
Wav2vec 2.0 (W2V2) has shown strong performance in pathological speech analysis by effectively capturing the characteristics of atypical speech. Despite its success, it remains unclear which components of its learned representations are…
Speaker embeddings are widely used in speaker verification systems and other applications where it is useful to characterise the voice of a speaker with a fixed-length vector. These embeddings tend to be treated as "black box" encodings,…