Study of spectral and temporal effects in the perception of noise degraded speech
01 Apr 2017-pp 1-4
TL;DR: An auditory simulation model is developed to extract and process the spectral and temporal features using Hilbert algorithm and significant improvement is achieved and hence this model should be helpful for enhancing the speech intelligibility of cochlear implant subjects.
Abstract: Cochlear Implants (CI) are surgically installed biomedical gadgets that give hearing to significantly hard of hearing individuals by direct electrical incitement of the auditory nerve. It has been recognized that auditory simulation models in cochlear implants improve the perception of speech significantly. For music and hearing perception in noisy environments, phase cue plays a major role but it is not being conveyed by the present day auditory models. This paper describes the results of a study on the spectro-temporal effects on the perception of English phonemes comprising vowels and consonants. An auditory simulation model is developed to extract and process the spectral and temporal features using Hilbert algorithm. Six English phonemes are presented to normal hearing listeners under various signal-to-noise ratios (SNR) and their speech intelligibility scores are computed. Significant improvement is achieved and hence this model should be helpful for enhancing the speech intelligibility of cochlear implant subjects.
Citations
More filters
TL;DR: A new developmental network that simulates the human auditory system and constructs an artificial auditory model for speech recognition that provides a new method to solve difficult problems, such as universal speech recognition, in traditional machine audition systems.
4 citations
TL;DR: In this paper , a review of noise reduction algorithms in cochlear implant technology is presented, focusing on recent interest in machine learning techniques and considering promising future areas of research in this area.
Abstract: Cochlear implant technology successfully restores hearing function to patients with sensory impairment. Although cochlear implant users generally hear well in quiet, they still find noisy conditions very challenging, hence the need to employ noise reduction algorithms in these systems to enhance the user experience. This paper reviews noise reduction algorithms in cochlear implants. Traditionally, such algorithms have been classified as either single- or multiple-channel, depending on the number of microphones they use. This review retains this general classification in looking at recent papers and extends it to reflect recent interest in machine learning techniques. The review concludes with consideration of promising future areas of research.
2 citations
TL;DR: Experimental results show the advantage of the proposed DNN compared to the state-of-the-art methods for the recognition accuracies of English words and phrases.
Abstract: Speech recognition performance of the machine has been greatly improved using artificial intelligence. However, compared with the superior recognition ability of human auditory system, the machine ...
Cites background from "Study of spectral and temporal effe..."
...Unfortunately, many existing literatures (Alam, Jassim, & Zilany, 2014; Mahalakshmi & Reddy, 2017; Prasetio & Hayashida, 2017) used symbolic methods to model the auditory pathway....
[...]
References
More filters
01 Sep 1993
TL;DR: A tutorial on signal processing in state-of-the-art speech recognition systems is presented, reviewing those techniques most commonly used, and three important trends that have developed in the last five years in speech recognition are examined.
Abstract: A tutorial on signal processing in state-of-the-art speech recognition systems is presented, reviewing those techniques most commonly used. The four basic operations of signal modeling, i.e. spectral shaping, spectral analysis, parametric transformation, and statistical modeling, are discussed. Three important trends that have developed in the last five years in speech recognition are examined. First, heterogeneous parameter sets that mix absolute spectral information with dynamic, or time-derivative, spectral information, have become common. Second, similarity transform techniques, often used to normalize and decorrelate parameters in some computationally inexpensive way, have become popular. Third, the signal parameter estimation problem has merged with the speech recognition process so that more sophisticated statistical models of the signal's spectrum can be estimated in a closed-loop manner. The signal processing components of these algorithms are reviewed. >
792 citations
TL;DR: The greatest benefits with cochlear implantation have occurred in patients who (1) acquired speech and language before their hearing loss, and (2) have shorter duration of deafness.
Abstract: Cochlear implants have been very successful in restoring partial hearing to profoundly deaf people. Many individuals with implants are now able to communicate and understand speech without lip-reading, and some are able to talk over the phone. Children with implants can develop spoken-language skills and attend normal schools (i.e., schools with normal-hearing children). The greatest benefits with cochlear implantation have occurred in patients who (1) acquired speech and language before their hearing loss, and (2) have shorter duration of deafness. Gradual, but steady, improvements in speech production and speech perception have also occurred in prelingually deafened adults or children.
225 citations
"Study of spectral and temporal effe..." refers background in this paper
...Hearing sense is accomplished by electrically stimulating the sound-related nerve [1]....
[...]
TL;DR: The author discusses the accomplishments and challenges in treating sensorineurnal deafness through electrical stimulation with a focus on the treatment of the central nervous system.
Abstract: The author discusses the accomplishments and challenges in treating sensorineurnal deafness through electrical stimulation.
101 citations
"Study of spectral and temporal effe..." refers background in this paper
...The sound signals are received and transmitted to the inside part (recipient stimulator) and are passed on as electrical signals through the electrode array straightforwardly to the sound-related nerve [3]....
[...]
TL;DR: Analysis of three potentially informative acoustic properties present during consonants and vowels for monosyllabic words and sentences suggests that speech information transmitted by the envelope is responsible, in part, for greater vowel contributions in sentences, but is not predictive for isolated words.
Abstract: The speech signal contains many acoustic properties that may contribute differently to spoken word recognition. Previous studies have demonstrated that the importance of properties present during consonants or vowels is dependent upon the linguistic context (i.e., words versus sentences). The current study investigated three potentially informative acoustic properties that are present during consonants and vowels for monosyllabic words and sentences. Natural variations in fundamental frequency were either flattened or removed. The speech envelope and temporal fine structure were also investigated by limiting the availability of these cues via noisy signal extraction. Thus, this study investigated the contribution of these acoustic properties, present during either consonants or vowels, to overall word and sentence intelligibility. Results demonstrated that all processing conditions displayed better performance for vowel-only sentences. Greater performance with vowel-only sentences remained, despite removing dynamic cues of the fundamental frequency. Word and sentence comparisons suggest that the speech envelope may be at least partially responsible for additional vowel contributions in sentences. Results suggest that speech information transmitted by the envelope is responsible, in part, for greater vowel contributions in sentences, but is not predictive for isolated words.
71 citations
03 Aug 2010
TL;DR: The design of an analog complex gammatone filter is introduced in order to extract both envelope and phase information of the incoming speech signals as well as to emulate the basilar membrane spectral selectivity.
Abstract: According to recent physiological experiments, the envelope and phase of speech signals are required to enhance the perceptive capability of a cochlear implant processor. In this paper, the design of an analog complex gammatone filter is introduced in order to extract both envelope and phase information of the incoming speech signals as well as to emulate the basilar membrane spectral selectivity. The gammatone impulse response is first transformed into the frequency domain and the resulting 8th-order transfer function is subsequently mapped onto a state-space description of an orthonormal ladder filter. Using this approach, the real and imaginary transfer functions that share the same denominator can be extracted using two different C matrices. This results in a compact filter structure. The proposed filter is designed using G m -C integrators and sub-threshold CMOS devices in AMIS 0.35μm technology. Simulation results using Cadence RF Spectre confirm the design principle and ultra low power operation.
24 citations