Remote Speech Recognition Research Articles

Remote collection of speech recognition data: Considerations for testing children

This talk will provide an overview of the methods and lessons learned over the course of three studies in which children’s masked speech recognition performance was assessed remotely. The first study evaluated the binaural intelligibility level difference in typically developing children using families’ personal computers and headphones. The second study examined the impact of face coverings on consonant identification in noise with and without access to visual cues. Participants were children with and without hearing loss. The third experiment evaluated the feasibility of remote speech recognition testing for children with Down syndrome. The latter two experiments entailed providing families with laboratory hardware, following appropriate social distancing and infection control measures. Findings from all three studies will be discussed, highlighting comparisons with data obtained in the laboratory. Recommendations for remote studies involving children will be provided, based on our experiences and the resultant data.

The Lineal Prediction Applied to Distributed Speech Recognition in IP Nets

This work presents results in the application of speech compression to speech recognition technics in IP nets. That’s why the three fundamental areas of the knowledge that are involved are: the voice compression, the transmission channels simulation and the speech recognition. This areas are integrated to achieve an application developed in MATLAB, able to carry out a remote speech recognition by means of the transmission of compressed voice, with the peculiarity that it is considered the probability of occurrence of losses of information in the transmission channels, in such way that the robustness of the proposed system is demonstrated.

Person-centred cochlear implant care: Assessing the need for clinic intervention in adults with cochlear implants using a dual approach of an online speech recognition test and a questionnaire

Objectives: To evaluate the feasibility of adults with cochlear implants using an online speech recognition test and questionnaire at home to assess whether they need to come to the clinic or not.Methods: A prospective single-centre feasibility study evaluating• An online speech recognition test (digit triplet test (DTT)).• A long-term follow-up questionnaire to assess aspects that a clinician would ask in a face-to-face appointment.• A satisfaction questionnaire to assess patient perception of remote speech recognition testing.• Seventeen people using cochlear implants aged from 34 to 84 years took part.Results:• The majority of adults were able and willing to use tools at home to assess if they need to come to the centre.• The DTT speech reception threshold was repeatable on three occasions within 3 weeks.• The majority of adults felt positive about testing their own hearing using the DTT at home. However, only a minority (two out of 17) felt they preferred remote testing to clinic testing (the majority was undecided).Conclusion: The concept of a dual approach of online speech recognition test and questionnaire both done at home has potential to identify which adults with cochlear implants require clinic intervention, although sensitivity and specificity measures are unknown. A clinic visit remains the gold standard of care, but remote care may supplement traditional care pathways.

The Development of Remote Speech Recognition Tests for Adult Cochlear Implant Users: The Effect of Presentation Mode of the Noise and a Reliable Method to Deliver Sound in Home Environments

The number of cochlear implant (CI) users is increasing annually, resulting in an increase in the workload of implant centers in ongoing patient management and evaluation. Remote testing of speech recognition could be time-saving for both the implant centers as well as the patient. This study addresses two methodological challenges we encountered in the development of a remote speech recognition tool for adult CI users. First, we examined whether speech recognition in noise performance differed when the steady-state masking noise was presented throughout the test (i.e. continuous) instead of the standard clinical use for evaluation where the masking noise stops after each stimulus (i.e. discontinuous). A direct coupling between the audio port of a tablet computer to the accessory input of the sound processor with a personal audio cable was used. The setup was calibrated to facilitate presentation of stimuli at a predefined sound level. Finally, differences in frequency response between the audio cable and microphones were investigated.

Ear sensor assembly for speech processing

An ear sensor apparatus includes a microphone positionable with respect to an ear canal (18) to detect sound signals from the ear canal and to generate a corresponding output signal. The apparatus may include a seal (20) for substantially blocking ambient sound signals from reaching the microphone and an interface (24) to convey the output signal to a remote speech recognition apparatus. The output signal may be normalized (42) so that the normalized output signal is more representative of speech from a user's mouth than speech detected from the user's ear.

Recognition of coded speech transmitted over wireless channels

Network-based speech recognition (NSR) and distributed speech recognition (DSR) have been proposed as solutions to translate speech recognition technologies to mobile environments. NSR is the most straightforward solution since it does not require any modification in the mobile phone, however DSR offers higher robustness against codec compression and transmission channel degradation. This paper explores an alternative approach for remote speech recognition which combines the advantages of NSR and DSR. In this scheme, a standard speech codec is used for speech transmission but the recognition is performed from the received codec parameters. In particular, we focus on the effect of transmission channel errors, which can cause a more severe performance reduction on speech recognition than codec distortion. First, we show that an NSR solution can approach DSR through a reconstruction technique along with an adapted noise reduction technique originally proposed for acoustic noise. Then, these results are improved by working with recognition features directly extracted from the codec bitstream by means of parameter transcoding. Required modifications on current networks in order to access the bitstream are described. The network upgrading with the tandem free operation (TFO) protocol is an attractive solution. This upgrade not only offers an overall improvement on the end-to-end speech quality, but would also allow a recognition performance similar, and even higher in poor channel conditions, to that obtained by DSR when parameter transcoding along with the proposed mitigation techniques are applied

A low-power integrated circuit for remote speech recognition

In this paper, a low-power, low-voltage speech processing system is presented. The system is intended to he used in remote speech recognition applications where feature extraction is performed on terminal and high-complexity recognition tasks and moved to a remote server accessed through a radio link. The proposed system is based on a CMOS feature extraction chip for speech recognition that computes 15 cepstrum parameters, each 8 ms, and dissipates 30 /spl mu/W at 0.9-V supply. Single-cell battery operation is achieved. Processing relies on a novel feature extraction algorithm using 1-bit A/D conversion of the input speech signal. The chip has been implemented as a gate array in a standard 0.5-/spl mu/m, three-metal CMOS technology. The average energy required to process a single word of the TI46 speech corpus is 10 /spl mu/J. It achieves recognition rates over 98% in isolated-word speech recognition tasks.