Rise time and formant transition duration in the discrimination of speech sounds: The Ba–Wa distinction in developmental dyslexia

Across languages, children with developmental dyslexia have a specific difficulty with the neural representation of the sound structure (phonological structure) of speech. One likely cause of their difficulties with phonology is a perceptual difficulty in auditory temporal processing (Tallal, 1980). Tallal (1980) proposed that basic auditory processing of brief, rapidly successive acoustic changes is compromised in dyslexia, thereby affecting phonetic discrimination (e.g. discriminating /b/ from /d/) via impaired discrimination of formant transitions (rapid acoustic changes in frequency and intensity). However, an alternative auditory temporal hypothesis is that the basic auditory processing of the slower amplitude modulation cues in speech is compromised (Goswami , 2002). Here, we contrast children's perception of a synthetic speech contrast (ba/wa) when it is based on the speed of the rate of change of frequency information (formant transition duration) versus the speed of the rate of change of amplitude modulation (rise time). We show that children with dyslexia have excellent phonetic discrimination based on formant transition duration, but poor phonetic discrimination based on envelope cues. The results explain why phonetic discrimination may be allophonic in developmental dyslexia (Serniclaes , 2004), and suggest new avenues for the remediation of developmental dyslexia. © 2010 Blackwell Publishing Ltd.

CLOSE—A Data-Driven Approach to Speech Separation

This paper studies single-channel speech separation, assuming unknown, arbitrary temporal dynamics for the speech signals to be separated. A data-driven approach is described, which matches each mixed speech segment against a composite training segment to separate the underlying clean speech segments. To advance the separation accuracy, the new approach seeks and separates the longest mixed speech segments with matching composite training segments. Lengthening the mixed speech segments to match reduces the uncertainty of the constituent training segments, and hence the error of separation. For convenience, we call the new approach Composition of Longest Segments, or CLOSE. The CLOSE method includes a data-driven approach to model long-range temporal dynamics of speech signals, and a statistical approach to identify the longest mixed speech segments with matching composite training segments. Experiments are conducted on the Wall Street Journal database, for separating mixtures of two simultaneous large-vocabulary speech utterances spoken by two different speakers. The results are evaluated using various objective and subjective measures, including the challenge of large-vocabulary continuous speech recognition. It is shown that the new separation approach leads to significant improvement in all these measures.

A Corpus-Based Approach to Speech Enhancement from Nonstationary Noise

Temporal dynamics and speaker characteristics are two important features of speech that distinguish speech from noise. In this paper, we propose a method to maximally extract these two features of speech for speech enhancement. We demonstrate that this can reduce the requirement for prior information about the noise, which can be difficult to estimate for fast-varying noise. Given noisy speech, the new approach estimates clean speech by recognizing long segments of the clean speech as whole units. In the recognition, clean speech sentences, taken from a speech corpus, are used as examples. Matching segments are identified between the noisy sentence and the corpus sentences. The estimate is formed by using the longest matching segments found in the corpus sentences. Longer speech segments as whole units contain more distinct dynamics and richer speaker characteristics, and can be identified more accurately from noise than shorter speech segments. Therefore, estimation based on the longest recognized segments increases the noise immunity and hence the estimation accuracy. The new approach consists of a statistical model to represent up to sentence-long temporal dynamics in the corpus speech, and an algorithm to identify the longest matching segments between the noisy sentence and the corpus sentences. The algorithm is made more robust to noise uncertainty by introducing missing-feature based noise compensation into the corpus sentences. Experiments have been conducted on the TIMIT database for speech enhancement from various types of nonstationary noise including song, music, and crosstalk speech. The new approach has shown improved performance over conventional enhancement algorithms in both objective and subjective evaluations.

Robust bimodal person identification using face and speech with limited training data and corruption of both modalities

This paper presents a novel method of audio-visual fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there is a limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new representation and a modified cosine similarity are introduced for combining and comparing bimodal features with limited training data as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal data set created from the SPIDRE and AR databases with variable noise corruption of speech and occlusion in the face images. The new method has demonstrated improved recognition accuracy.

Binaural Reproduction of Finite Difference Simulations Using Spherical Array Processing

Due to its efficiency and simplicity, the finite-difference time-domain method is becoming a popular choice for solving wideband, transient problems in various fields of acoustics. So far, the issue of extracting a binaural response from finite difference simulations has only been discussed in the context of embedding a listener geometry in the grid. In this paper, we propose and study a method for binaural response rendering based on a spatial decomposition of the sound field. The finite difference grid is locally sampled using a volumetric array of receivers, from which a plane wave density function is computed and integrated with free-field head related transfer functions, in the spherical harmonics domain. The volumetric array is studied in terms of numerical robustness and spatial aliasing. Analytic formulas that predict the performance of the array are developed, facilitating spatial resolution analysis and numerical binaural response analysis for a number of finite difference schemes. Particular emphasis is placed on the effects of numerical dispersion on array processing and on the resulting binaural responses. Our method is compared to a binaural simulation based on the image method. Results indicate good spatial and temporal agreement between the two methods.

Soft-core Stream Processing on FPGA: An FFT Case Study

The increasing design complexity associated with modern Field Programmable Gate Array (FPGA) has prompted the emergence of 'soft'-programmable processors which attempt to replace at least part of the custom circuit design problem with a problem of programming parallel processors. Despite substantial advances in this technology, its performance and resource efficiency for computationally complex operations remains in doubt. In this paper we present the first recorded implementation of a softcore Fast-Fourier Transform (FFT) on Xilinx Virtex FPGA technology. By employing a streaming processing architecture, we show how it is possible to achieve architectures which offer 1.1 GSamples/s throughput and up to 19 times speed-up against the Xilinx Radix-2 FFT dedicated circuit with comparable cost.

Wide Matching - An Approach to Improving Noise Robustness for Speech Enhancement

It is shown that under certain conditions it is possible to obtain a good speech estimate from noise without requiring noise estimation. We study an implementation of the theory, namely wide matching, for speech enhancement. The new approach performs sentence-wide joint speech segment estimation subject to maximum recognizability to gain noise robustness. Experiments have been conducted to evaluate the new approach with variable noises and SNRs from -5 dB to noise free. It is shown that the new approach, without any estimation of the noise, significantly outperformed conventional methods in the low SNR conditions while retaining comparable performance in the high SNR conditions. It is further suggested that the wide matching and deep learning approaches can be combined towards a highly robust and accurate speech estimator.

Perception of Filtered Speech by Children with Developmental Dyslexia and Children with Specific Language Impairments

Here we use two filtered speech tasks to investigate children’s processing of slow (<4 Hz) versus faster (∼33 Hz) temporal modulations in speech. We compare groups of children with either developmental dyslexia (Experiment 1) or speech and language impairments (SLIs, Experiment 2) to groups of typically-developing (TD) children age-matched to each disorder group. Ten nursery rhymes were filtered so that their modulation frequencies were either low-pass filtered (<4 Hz) or band-pass filtered (22 – 40 Hz). Recognition of the filtered nursery rhymes was tested in a picture recognition multiple choice paradigm. Children with dyslexia aged 10 years showed equivalent recognition overall to TD controls for both the low-pass and band-pass filtered stimuli, but showed significantly impaired acoustic learning during the experiment from low-pass filtered targets. Children with oral SLIs aged 9 years showed significantly poorer recognition of band pass filtered targets compared to their TD controls, and showed comparable acoustic learning effects to TD children during the experiment. The SLI samples were also divided into children with and without phonological difficulties. The children with both SLI and phonological difficulties were impaired in recognizing both kinds of filtered speech. These data are suggestive of impaired temporal sampling of the speech signal at different modulation rates by children with different kinds of developmental language disorder. Both SLI and dyslexic samples showed impaired discrimination of amplitude rise times. Implications of these findings for a temporal sampling framework for understanding developmental language disorders are discussed.