Statistical parametric synthesis offers numerous techniques to create new voices. Speaker adaptation is one of the most exciting ones. However, it still requires high quality audio data with low signal to noise ration and precise labeling. This paper presents an automatic speech recognition based unsupervised adaptation method for Hidden Markov Model (HMM) speech synthesis and its quality evalu...

This paper investigates the use of Multi-Distribution Deep Neural Networks (MD-DNNs) for integrating acoustic and statetransition models in free phone recognition of L2 English speech. In Computer-Aided Pronunciation Training (CAPT) system, free phone recognition for L2 English speech is the key model of Mispronunciation Detection and Diagnosis (MDD) in the cases of allowing freely speaking. A ...

We use goal babbling, a recent approach to bootstrapping inverse models, for vowel acquisition with an articulatory speech synthesizer. In contrast to motor babbling, goal babbling organizes exploration in a low-dimensional goal space. While such a goal space is naturally given in many motor learning tasks, the difficulty in modeling speech production lies within the complexity of acoustic feat...

In this paper, a framework for long audio alignment for conversational Arabic speech is proposed. Accurate alignments help in many speech processing tasks such as audio indexing, speech recognizer acoustic model (AM) training, audio summarizing and retrieving, etc. We have collected more than 1,400 hours of conversational Arabic besides the corresponding human generated non-aligned transcriptio...

We consider the problem of representing semantic concepts in speech by learning from untranscribed speech paired with images of scenes. This setting is relevant in low-resource speech processing, robotics, and human language acquisition research. We use an external image tagger to generate soft labels, which serve as targets for training a neural model that maps speech to keyword labels. We int...

In the present paper, we present evidence for the idea that speech motor learning is accompanied by changes to the neural coding of both auditory and somatosensory stimuli. Participants in our experiments undergo adaptation to altered auditory feedback, an experimental model of speech motor learning which like visuo-motor adaptation in limb movement, requires that participants change their spee...

There is a growing demand for embodied agents capable of engaging in face-to-face dialog using the same verbal and nonverbal behavior that people use. The focus of our work is generating coverbal hand gestures for these agents, gestures coupled to the content and timing of speech. A common approach to achieve this is to use motion capture of an actor or hand-crafted animations for each utteranc...

agents, in a multi agent system, communicate with each other through the process of exchanging messages which is called dialogue. multi agent organization is generally used to optimize agents’ communications. holonic organization demonstrates a self-similar recursive and hierarchical structure in which each holon may include some other holons. in a holonic system, lateral communication occurs b...

This paper presents speech-driven Web retrieval models which accepts spoken search topics (queries) in the NTCIR-3 Web retrieval task. We experimentally evaluate the techniques of combining outputs of multiple LVCSR models with a language model(LM) with a 60,000 vocabulary size in recognition of spoken queries. As model combination techniques, we use the SVM learning. We show that the technique...

A neuronal model intended to target highly sonorant periods of a speech stream is presented. The model—“Spike-V”—uses habituation and Hebbian learning in opposition to each other to dynamically adjust its behavior. Acting in realtime, driven by only the signal, Spike-V produces a spike-train in which each spike corresponds to roughly the center of a period of high sonority (i.e. a vowel) in the...