Current Automatic Speech Recognition systems convert the speech signal into a sequence of discrete units, such as phonemes, and then apply statistical methods on the units to produce the linguistic message. Similar methodology has also been applied to recognize speaker and language, except that the output of the system can be the speaker or language information. Therefore, we propose the use of...

In this paper, we investigate achievable rates for data transmission from sources to sinks through multiple relay networks. We consider myopic coding, a constrained communication strategy in which each node has only a local view of the network, meaning that nodes can only transmit to and decode from neighboring nodes. We compare this with omniscient coding, in which every node has a global view...

Speaker verification systems require some kind of background model to reliably perform the verification task. Several algorithms have been proposed for the selection of cohort models to form a background model. This paper proposes a new cohort selection method called the Close Impostor Clustering (CIC). The new method is shown to outperform several other methods in a text-dependent verification...

Recent auditory physiological evidence points to a modulation frequency dimension in the auditory cortex. This dimension exists jointly with the tonotopic acoustic frequency dimension. Thus, audition can be considered as a relatively slowly-varying two-dimensional representation, the “modulation spectrum,” where the first dimension is the well-known acoustic frequency and the second dimension i...

State-of-the-art speech recognition systems are trained using human transcriptions of speech utterances. In this paper, we describe a method to combine active and unsupervised learning for automatic speech recognition (ASR). The goal is to minimize the human supervision for training acoustic and language models and to maximize the performance given the transcribed and untranscribed data. Active...

Sine-wave speech (SWS) is a three-tone replica of speech, conventionally created by matching each constituent sinusoid in amplitude and frequency with the corresponding vocal tract resonance (formant). We propose an alternative technique where we take a high-quality multicomponent sinusoidal representation and decimate this model so that there are only three components per frame. In contrast to...

In this paper a new pre-processor for a free speech transcription system is described. It performs a speech/non-speech partition, a segmentation of the speech parts into speaker turns, and a clustering of the speaker turns. It works in a stream-based mode, and it is aiming for a high accuracy with a low delay and processing time. Experiments on the Hub4 Broadcast News corpus show that the newly...

In this paper, we investigate the performance of a downlink multiple-input multiple-output (MIMO) multicarrier code division multiple access (MC-CDMA) system employing a receiver with iterative channel estimation (ICE). The MC-CDMA system transmits several data symbols per user and per orthogonal frequency division multiplexing (OFDM) symbol in parallel, with each data symbol being spread with ...

This paper presents a model to predict the phrase commands of the Fujisaki Model for F0 contour for the Portuguese Language. Phrase commands location in text is governed by a set of weighted rules. The amplitude (Ap) and timing (T0) of the phrase commands are predicted in separate neural networks. The features for both neural networks are discussed. Finally a comparison between target and predi...

Developing applications for parallel and distributed systems is hard due to their nondeterministic nature; developing debugging tools for such systems and applications is even harder. A number of distributed debugging tools and techniques exist; however, we believe that they lack the infrastructure to scale to large-scale distributed systems, systems with hundreds and thousands of nodes, such a...