50-word Lists Research Articles

A Greek Pediatric Word Recognition Test by Picture Identification.

(1) Background: The study aimed to construct a clinically valuable closet-set WRS test with a picture identification task for young Greek-speaking children. (2) Methods: The test material was meticulously designed based on specific criteria. To determine which parts of speech are used more frequently by preschool children, a spontaneous speech sample (250 words per child) was acquired from three hundred children aged 3 to 6 years (M = 4.56, SD = 0.90). The study involved the development and application of two phonemically balanced 50-word lists suitable for young children, as well as the creation of picture representations for each response set. All testing was accomplished in an audiometric booth that exceeded the audiometric rooms' ambient noise level standards. The speech signal was routed from a laptop computer to a GSI 61 audiometer, and all test items were delivered from the audiometer to the subject. (3) Results: The results indicated that materials for a WRS test for young children are developed with high face validity and are applicable for children as young as three years old. The test satisfies the essential components needed for a WRS test. It consists of two phonemically balanced 50-word lists with low-redundancy bisyllabic words, with each list containing 227 phonemes. (5) Conclusions: This novel closed-set WRS test presents a valuable tool for assessing speech perception skills in young Greek-speaking children. The test results have various applications, including diagnosis, research, and (re)habilitation.

Validating Four Hmong Word Recognition Tests With Normal-Hearing Bilingual Hmong Individuals

The purpose of this study was to validate four digitally recorded and phonetically balanced 50-word recognition lists in the White Hmong dialect with normal-hearing bilingual Hmong adults. Using a randomized, incomplete-block design, each participant listened to and repeated four unique Hmong lists delivered by a female and a male talker. Participants were also tested with an English word list-List 1A of the Northwestern University Auditory Test No. 6. Participants' correct pronunciation of each word was scored. A nonparametric Mann-Whitney U Location Difference Test for Equivalence using two one-sided tests equivalence hypothesis: -0.02 < [(List_1) - (List_2)] < 0.02 was conducted to assess equivalence among all four Hmong and the English lists. Seventy Hmong speakers participated in this study (35 women, 35 men; M age = 29.5 years, SD = 7.1). In all four Hmong lists, 93.5% (187/200) words met the validation criteria for ≥ 92% correct pronunciation. The 13 difficult words were deemed adequate by a Hmong panel and, therefore, were included to maintain four unique, balanced word lists. The test revealed that the Hmong and English word lists were considered equivalent at the 2% bound. The four Hmong word lists were validated to ensure an equal range of word difficulty across the lists.

Psychometric Function Characteristics of Time- Compressed Persian Words

Background and Aim: The psychometric function characteristics (e.g. threshold and slope) of the time-compressed words have not been investigated in previous studies to compile psychometrically homogeneous word lists. Therefore, this study aimed to investigate psychometric function characteristics of monosyllabic time-compressed Persian words to develop psychometrically equivalent time-compressed word lists. Methods: Two hundred most common monosyllabic words in Persian language were time- compressed at a rate of 40%-85% and presented to 21 participants with normal hearing at a fixed intensity level. The threshold and slope of the psychometric function for all words were determined using the logistic regression. The compression ratio (CR) for 5%-95% correct recognition was predicted based on the psychometric function fitted to the measured correct recognition score. Results: Mean CR 50% of the words was in a range of 53%-78%. The mean CR 50% and slope were not significantly different between consonant-vowel-consonant and consonant- vowel-consonant-consonant words. The predicted CR for 5%-95% correct recognition varied from 61.5% to 88.4%. The final result was two 50-word lists of monosyllabic words with the same mean threshold and slope. Conclusion: Persian time-compressed monosyllabic words have different CR 50% and slope that may interact with their intelligibility. Keywords: Time compression; intelligibility; psychometric function; Persian monosyllabic words

A Comparison of Word-Recognition Performances on the Auditec and VA Recorded Versions of Northwestern University Auditory Test No. 6 by Young Listeners with Normal Hearing and by Older Listeners with Sensorineural Hearing Loss Using a Randomized Presentation-Level Paradigm.

The Auditec of St. Louis and the Department of Veterans Affairs (VA) recorded versions of the Northwestern University Auditory Test No. 6 (NU-6) are in common usage. Data on young adults with normal hearing for pure tones (YNH) demonstrate equal recognition performances on the two versions when the VA version is presented 5 dB higher but similar data on older listeners with sensorineural hearing loss (OHL) are lacking. To compare word-recognition performances on the Auditec and VA versions of NU-6 presented at six presentation levels with YNH and OHL listeners. A quasi-experimental, repeated-measures design was used. Twelve YNH (M = 24.0 years; PTA = 9.9-dB HL) and 36 OHL listeners (M = 71.6 years; PTA = 26.7-dB HL) participated in three, one-hour sessions. Each listener received 100 stimulus words that were randomized by 6 presentation levels for each of two speakers (YNH, -2 to 28-dB SL; OHL, -2 to 38-dB SL). The sessions were limited to 25 practice and 400 experimental words. Digital versions of the 16, 25-word tracks for each session were alternated between speakers. Each of the 48 listeners had higher recognition performances on the Auditec version of NU-6 than on the VA version. The respective overall recognition performances on the Auditec and VA versions were 71.4% and 64.1% (YNH) and 68.7% and 58.2% (OHL). At the highest presentation levels, recognition performances on the two versions differed by only 0.5% (YNH) and 3.3% (OHL). At the 50% correct point, performances on the Auditec version were 3.2 dB (YNH) and 6.1 dB (OHL) better than those on the VA version. The slopes at the 50% points on the mean functions for both speakers were about 4.9%/dB (YNH) and 3.0%/dB (OHL); however, the slopes evaluated from the individual listener data were steeper, 5.2 to 5.3%/dB (YNH) and 3.3 to 3.5%/dB (OHL). When the individual data were transformed from dB SL to dB HL, the differences between the two listener groups were emphasized. The four functions (2 speakers by 2 listener groups) were plotted for each of the 48 participants and each of the 200 words, which revealed the gamut of relations among the datasets. Examination of the data for each speaker across test sessions, in the traditional 50-word lists, and in the typically used 25-word lists of Randomization A revealed no differences of clinical concern. Finally, introspective reports from the listeners revealed that 91.7% and 83.3% of the YNH and OHL listeners, respectively, thought the Auditec speaker was easier to understand than the VA speaker. Recognition performances on each participant and on each word are presented.

Clinical Strategies for Sampling Word Recognition Performance

Computer simulation was used to estimate the statistical properties of searches for maximum word recognition ability (PB max). These involve presenting multiple lists and discarding all scores but that of the 1 list that produced the highest score. The simulations, which model limitations inherent in the precision of word recognition scores, were done to inform clinical protocols. A secondary consideration was a derivation of 95% confidence intervals for significant changes in score from phonemic scoring of a 50-word list. The PB max simulations were conducted on a "client" with flat performance intensity functions. The client's performance was assumed to be 60% initially and 40% for a second assessment. Thousands of estimates were obtained to examine the precision of (a) single lists and (b) multiple lists using a PB max procedure. This method permitted summarizing the precision for assessing a 20% drop in performance. A single 25-word list could identify only 58.4% of the cases in which performance fell from 60% to 40%. A single 125-word list identified 99.8% of the declines correctly. Presenting 3 or 5 lists to find PB max produced an undesirable finding: an increase in the word recognition score. A 25-word list produces unacceptably low precision for making clinical decisions. This finding holds in both single and multiple 25-word lists, as in a search for PB max. A table is provided, giving estimates of 95% critical ranges for successive presentations of a 50-word list analyzed by the number of phonemes correctly identified.

The homogeneity with respect to intelligibility of recorded word-recognition materials.

In developing the PB-50 word lists, J. P. Egan suggested five developmental principles, two of which were "equal average difficulty" and an "equal range of difficulty" among the lists (page 963). Egan was satisfied that each of the 20 PB-50 lists had equivalent ranges of recognition performances and that the lists produced the same average performances. This was accomplished in preliminary studies that measured the recognition performance of each word and eliminated words that were always or never correct. In preparing for studies of interrupted words, we needed to know the range of difficulty inherent in the speaker specific NU-6 and Maryland CNC materials we planned to use when those words were not interrupted. There were only a few studies in the literature that touched on the range of difficulty characteristic of the word-recognition materials in common usage. The paucity of this information prompted this investigation whose scope broadened to include the CID W-22, Maryland CNC, NU-6, and PB-50 materials spoken by a variety of speakers. The purpose was to evaluate the homogeneity with respect to intelligibility of the words that comprise several of the common word-recognition materials used in audiologic evaluations. Both retrospective (10) and prospective (3) studies were involved. Data from six of the retrospective studies were from our labs. The prospective studies involved both listeners with normal hearing for pure tones and listeners with sensorineural hearing loss. The sample sizes for the 13 data sets ranged from 24 to 1,030, with 24 the typical number for listeners with normal hearing. The retrospective data were from published studies and archived data from our laboratories. The prospective studies involved presentation of the word-recognition materials to the listeners at a comfortable level. An item analysis was conducted on each data set with descriptive statistics used to characterize the data. Additionally, skewness coefficients were calculated on the distributions of word performances and the interquartile range was used to determine minor and major outliers within each set of 200 words and their component 50-word lists (300 words for the Maryland CNCs). For listeners with normal hearing the majority of performances on the words within a 50-word list were better than the mean performance, which produced negatively skewed distributions with outlier performances in every list. For listeners with sensorineural hearing loss the performances on the words within a 50-word list were evenly distributed above and below the mean performance, which yielded essentially normal distributions with few outliers. There were a few words on which performances were better by the listeners with hearing loss. Every list of word-recognition materials has a few words on which recognition performances are noticeably poorer than performances on the majority of the remaining words. If the intention of an experiment is to evaluate performance at the word level, then identifying these "outliers" becomes a necessity. Although not evaluated in this report, the implications for 25-word lists are they should be based on recognition-performance data and not compiled arbitrarily.

Identification and response latencies for Mandarin-accented isolated words in quiet and in noise

This study compared the intelligibility of native and foreign-accented American English speech presented in quiet and mixed with two different levels of background noise. Two native American English speakers and two native Mandarin Chinese speakers for whom English is a second language read three 50-word lists of phonetically balanced words (Stuart, 2004). The words were mixed with noise at three different signal-to-noise levels—no noise (quiet), SNR + 10 dB (signal 10 dB louder than noise) and SNR 0 (signal and noise at equal loudness). These stimuli were presented to ten native American English listeners who were simply asked to repeat the words they heard the speakers say. Listener response latencies were measured. The results showed that for both native and accented speech, response latencies increased as the noise level increased. For words identified correctly, response times to accented speech were longer than for native speech but the noise conditions affected both types equally. For words judged incorrectly, however, the noise conditions increased latencies for accented speech more than for native speech. Overall, these results support the notion that processing accented speech requires more cognitive effort than processing native speech.

A Demonstration of Improved Precision of Word Recognition Scores

PURPOSE The purpose of this study was to demonstrate improved precision of word recognition scores (WRSs) by increasing list length and analyzing phonemic errors. METHOD Pure-tone thresholds (frequencies between 0.25 and 8.0 kHz) and WRSs were measured in 3 levels of speech-shaped noise (50, 52, and 54 dB HL) for 24 listeners with normal hearing. WRSs were obtained for half-lists and full lists of Northwestern University Test No. 6 (Tillman & Carhart, 1966) words presented at 48 dB HL. A resampling procedure was used to derive dimensionless effect sizes for identifying a change in hearing using the data. This allowed the direct comparison of the magnitude of shifts in WRS (%) and in the average pure-tone threshold (dB), which provided a context for interpreting the WRS. RESULTS WRSs based on a 50-word list analyzed by the percentage of correct phonemes were significantly more sensitive for identifying a change in hearing than the WRSs based on 25-word lists analyzed by percentage of correct words. CONCLUSION Increasing the number of items that contribute to a WRS significantly increased the test's ability to identify a change in hearing. Clinical and research applications could potentially benefit from a more precise word recognition test, the only basic audiologic measure that estimates directly the distortion component of hearing loss and its effect on communication.

The ready to learn evaluation: characterising neurodevelopmental problems identified at a universal nurse contact with 30 month old children

Aims ▶To assess the prevalence of language delay and social/emotional difficulties in a population of children at 30 months old ▶To assess the overlap between language delay and social/emotional difficulties ▶To assess the acceptability and feasibility of the new routine 30 month contact for health visitors. Methods Families of 30 month old children were offered a visit from their health visitor. Structured data were collected relating to language, social and emotional development using three instruments; The Strengths and Difficulties Questionnaire (SDQ), the abbreviated Sure Start Language Measure and a two-item language screen. Based on the results of these measures, children were then allocated into one of three groups: 1) difficulties on SDQ only; 2) language difficulties only; and 3) both SDQ and language difficulties. Results There was an 83% return rate of contact forms from the health visitors. We have partial data on 474 / 570 (83%) children and full data on 415/570 (73%) of the sample of eligible children. Data on language delay are presented in table 1: Data on SDQ abnormalities are presented in table 2: There were highly significant correlations between language delay and social and emotional difficulties, with similar results observed with each of the language measures. Furthermore, problem scores on each of the SDQ subscales were highly correlated with the SSLM 50-word list. Conclusion Language delay and social and emotional problems are highly correlated with adverse physical, mental health and forensic outcomes in adulthood; there is the potential for their early detection in childhood. A significant proportion of children were identified as having both language and social and emotional difficulties through this pilot 30m contact. The potential for early identification and intervention resulting from this contact is substantial and, if it were rolled out to the wider population, could improve the health and social outcomes of a generation.

Computer-mediated assessment of intelligibility in aphasia and apraxia of speech

Background: Previous work indicates that single-word intelligibility tests developed for dysarthria are sensitive to segmental production errors in aphasic individuals with and without apraxia of speech. However, potential listener learning effects and difficulties in adapting elicitation procedures to coexisting language impairments limit their applicability to left hemisphere stroke survivors. Aims: The main purpose of this study was to examine basic psychometric properties for a new monosyllabic intelligibility test developed for individuals with aphasia and/or AOS. A related purpose was to examine clinical feasibility and potential to standardise a computer-mediated administration approach. Methods & Procedures: A 600-item monosyllabic single-word intelligibility test was constructed by assembling sets of phonetically similar words. Custom software was used to select 50 target words from this test in a pseudo-random fashion, and to elicit and record production of these words by 23 speakers with aphasia and 20 neurologically healthy participants. To evaluate test–retest reliability, two identical sets of 50-word lists were elicited by requesting repetition after a live speaker model. To examine the effect of a different word set and auditory model, an additional set of 50 different words was elicited with a pre-recorded model. The recorded words were presented to normal-hearing listeners for identification via orthographic and multiple-choice response formats. To examine construct validity, production accuracy for each speaker was estimated via phonetic transcription and rating of overall articulation. Outcomes & Results: Recording and listening tasks were completed in less than 6 minutes for all speakers and listeners. Aphasic speakers were significantly less intelligible than neurologically healthy speakers and displayed a wide range of intelligibility scores. Test–retest and inter-listener reliability estimates were strong. No significant difference was found in scores based on recordings from a live model versus a pre-recorded model, but some individual speakers favoured the live model. Intelligibility test scores correlated highly with segmental accuracy derived from broad phonetic transcription of the same speech sample and a motor speech evaluation. Scores correlated moderately with rated articulation difficulty. Conclusions: We describe a computerised, single-word intelligibility test that yields clinically feasible, reliable, and valid measures of segmental speech production in adults with aphasia. This tool can be used in clinical research to facilitate appropriate participant selection and to establish matching across comparison groups. For a majority of speakers, elicitation procedures can be standardised by using a pre-recorded auditory model for repetition. This assessment tool has potential utility for both clinical assessment and outcomes research.

Speech Intelligibility and Passive, Level-Dependent Earplugs

Noise-induced hearing loss is one of the most common occupational diseases. Military personnel are at especially high risk due to the broad range of military noise hazards and the frequency of exposure. Hearing protectors are vital for this particular workforce, yet they can impede the ability to understand necessary communication in the field. Level-dependent hearing protectors are designed to protect the auditory system from the hazards of impulse noise, while preserving the ability to hear speech and other important auditory signals. The aim of this study was to evaluate the effect of two different passive, level-dependent earplugs (Combat Arms Earplugs; Sonic II Ear valves) on speech understanding of normal-hearing listeners in the presence of low-level background noise. The Combat Arms Earplug, developed specifically for use by military personnel, represented devices that attenuate impulse noise using small orifices and the Sonic II ear valve represented devices using an internal diaphragm. This study used a repeated-measures experimental design. Four scrambled lists of each of the four Northwestern University No. 6 50-word lists were presented in random order at 65 dB SPL in the presence of quiet and two different types of background noise: multitalker and military vehicle noise; using three ear conditions: NP (open ear), CA (Combat Arms Earplugs), and SO (Sonic II earplugs); and three signal-to-noise ratios (SNRs): -10, 0, and +10 dB. Word recognition scores (WRSs) of 18 native English-speaking adults with normal hearing sensitivity were measured in all test conditions. The percentage of words correctly repeated was used to determine differences between the two different level-dependent devices, types of background noise, and SNRs. Results showed a statistically significant increase in WRS as SNR increased from -10 to +10 dB. A repeated-measures analysis of variance for ear condition × noise × SNR indicated a significant main effect for SNR but not for type of noise or ear condition. A slight but significant interaction was found for SNR and ear condition. SNR had great impact on the ability of listeners to understand speech in the presence of background noise; however, the type of noise and the type of level-dependent device used did not. The results of the study support the notion that individuals potentially subjected to high-level impulse noise should be able to use level-dependent earplugs in low-level continuous noise without compromising speech understanding. More specifically, the passive, level-dependent earplugs currently used by military personnel do not appear to be detrimental to speech communication for listeners with normal hearing when the speech is at an average conversational level and the listener is actively attending to the signal.

Effect of age, presentation method, and learning on identification of noise-vocoded words

Noise vocoding was used to investigate the ability of younger and older adults with normal audiometric thresholds in the speech range to use amplitude envelope cues to identify words. In Experiment 1, four 50-word lists were tested, with each word presented initially with one frequency band and the number of bands being incremented until it was correctly identified by the listener. Both age groups required an average of 5.25 bands for 50% correct word identification and performance improved across the four lists. In Experiment 2, the same participants who completed Experiment 1 identified words in four blocked noise-vocoded conditions (16, 8, 4, 2 bands). Compared to Experiment 1, both age groups required more bands to reach the 50% correct word identification threshold in Experiment 2, 6.13, and 8.55 bands, respectively, with younger adults outperforming older adults. Experiment 3 was identical to Experiment 2 except the participants had no prior experience with noise-vocoded speech. Again, younger adults outperformed older adults, with thresholds of 6.67 and 8.97 bands, respectively. The finding of age effects in Experiments 2 and 3, but not in Experiment 1, seems more likely to be related to differences in the presentation methods than to experience with noise vocoding.

Quality Indicators for the Care of Hearing Loss in Vulnerable Elders

on quality of life. 3 Use of hearing aids or surgical intervention improves hearing and has a positive effect on quality of life. 4‐6 A number of screening tests have been developed for hearing loss and are the focus of two of the quality indicators (QIs) listed below. These tests will be described in more detail below. To confirm the presence of hearing loss, formal testing (audiogram) is necessary. Formal audiological testing is performed in a sound-protected setting and takes 30 to 60 minutes to complete. The patient’s auditory threshold (pure-tone threshold) is assessed for frequencies from 500 to 8,000Hz. The patient indicates the minimum decibel level at which a sound is perceived. Speech recognition is examined by having the patient listen to monosyllabic words at a comfortable listening level (usually 40dB above speech threshold) and recording the percentage of correctly repeated words using a 50-word list. The two major forms of hearing loss are sensorineural and conductive hearing loss. Sensorineural hearing loss is more common and is associated with aging. Sensorineural hearing loss due to aging is termed presbycusis. This type of hearing loss typically occurs gradually over decades. Damage is at the neural level, including the hair cells in the inner ear. Because no treatment is available to reverse this damage, sensorineural hearing loss is usually treated with amplification. Alternatively, conductive loss results from mechanical abnormalities of the middle and external ear and may result from the presence of foreign bodies, fluid (otitis media), or ossicular discontinuities. In general, these losses respond best to surgical intervention. In summary, hearing impairment is not only prevalent but also burdensome in the older population. Early diagnosis and treatment of hearing impairment can improve quality of life and functional status in the aging population.

A Comparison of Two Approaches to Assessment of Speech Recognition Ability in Single Cases

Single-case design with the randomization test (RT) has been proposed as an alternative to the binomial distribution (BD) tables of Thornton and Raffin (1978) to assess changes in speech recognition performance in individual subjects. The present study investigated whether data analyzed using both approaches would result in similar outcomes. Sixty-two adults with normal hearing were evaluated using phoneme scoring and a restricted alternating treatments design under two signal-to-noise conditions. Results revealed a significant correlation between the RT and a BD analysis using at least 50-word lists, although the BD analysis was a more sensitive measure. The absence of correlation between the RT with a BD analysis using 25-word lists challenges the common clinical practice of using reduced list size, and supports the use of phoneme scoring and other attempts to find clinically acceptable yet evidence-based solutions to overcome the conflict between time and accuracy.

Reliability of threshold, slope, and PB max for monosyllabic words.

The Auditec recordings of the CID W-22 monosyllables were used to generate test and retest intelligibility functions on normally hearing listeners and subjects with mild-to-moderate sensorineural hearing loss. The normally hearing subjects were tested with 50-word lists at SPLs ranging from 15 to 50 dB. Lists of 25 words were used with the hearing-impaired group. The functions were analyzed to assess the reliability of threshold (50% point), slope (20%-80% points), and maximum intelligibility (PB max). The 50% point was obtained at 28 dB SPL for the normally hearing listeners and at a sensation level (SL) of 12 dB respondaic thresholds for the hearing-impaired group. Very stable monosyllabic thresholds were found because 95% of the test-retest values were within 6 dB for both subject groups. Slopes of 4.9% per dB and 2.7% per dB were obtained for the normally hearing and hearing-impaired groups, respectively. Fair reliability was observed; 95% of the test-retest values encompassed a range of +/- 1.9% per dB for the normally hearing subjects and +/- 1.1% per dB for the hearing-impaired group. Although group slopes provide useful information for selecting the range and step size for generating psychometric functions, the value of routinely obtaining slope on an individual basis has not been demonstrated. Even though the same word lists were used for both test and retest measurements, reliability closely agreed with predicted results based on the binomial theorem. In contrast to the large variability for a single list of 25 words, very stable PB max scores were found when two or three scores were averaged on the plateau of the function.

Identification of words and manner features of speech by two profoundly deaf teenagers using a tactile vocoder

Two prelingually profoundly deaf teenage girls were taught to identify “live-voice” English words while wearing a tactile voder. To ensure the subject's deafness, hearing aids were removed and earplugs and headphones carrying white noise were worn. The reader sat out of sight from the subject so lipreading information could not be obtained. Words were introduced two or three at a time until the subject reached criterion on a 50-word list. The two subjects acquired a tactual vocabulary of 50 words with 21 and 25 h of training, respectively. Immediately after these word identification tests, experiments were carried out to test the subject's ability to identify the “manner of articulation” features of speech. Subjects could identify whether CV's contained a nasal, liquid voiced stop, unvoiced stop, or unvoiced fricative with accuracies ranging from 75% to 100% correct.

Autonomic responsivity during recognition memory processing in three age groups.

Thirty male volunteers in the age groups of young (18-34 years), middle-aged (35-54 years), and old (55-72 years) performed a recurrent recognition task of eight emotional and eight neutral words embedded in balanced 50-word lists while their electrodermal (EDR), heart rate (HR), and recognition responses were recorded. During testing, two hours and again one week following presentation of the 16 words, no marked differences among age groups were observed in EDR, but HR responses were lower in the old than in the young group. The old adopted high signal detection decision criteria for emotional words, which accounted for their lower recognition of emotional words in one measure. The old were as proficient as the young in recognition of neutral words. More emotional words were correctly recognized when a person's responsivity in HR and EDR was high, but this correlation was dissociated in the old. Heart rate changes but not EDR reflected a reduced responsivity in the old. The results place in question the use of peripheral autonomic measures as an index to memory processing.

A clinician-judged technique for quantifying dysarthric speech based on single-word intelligibility

A clinician-judged technique for quantifying dysarthric speech based on single-word intelligibility was developed and evaluated in three experiments. Dysarthric speakers were audio-recorded as they read 50-word lists that had been randomly generated from sets of similar sounding words. These tapes were judged by speech pathologists using listening formats that were systematically altered by varying the number of choices available to the judges. Results indicated that some formats were more sensitive to differences that exist among severely dysarthric speakers and others were more sensitive to differences that exist among mild to moderately dysarthric speakers. Judge familiarity with the master word pool increased scores slightly but in a consistent and predictable fashion. Scores from different randomly generated word lists were similar when the influence of a speaker's day-to-day variability was controlled. Clinical implications and uses of this technique for the monitoring of change in speaker performance were discussed.

The effect of masking by noise on word discrimination scores in listeners with normal hearing and with noise-induced hearing loss.

Patients with high-frequency hearing loss often complain at the Workers' Compensation Board that they find it difficult to hear speech in a noisy environment. This study was undertaken to test the validity of their complaints. The experiment had a 2x3x3 factorial design. The factors were subject group (normal hearing versus sensorineural hearing loss), stimulus level (65, 75, and 85 dB SPL), and speech-to-noise ratio (5, 12, and 19 dB). There were 6 subjects in each condition. Each subject was tested for his speech discrimination with three CID W-22 50-word lists, one in each of the three different speech-to-noise ratios. Both speech and pink noise were presented through loudspeakers in a sound field. The results support the patients' complaints. Possible explanations for the results are discussed.

Reliability in the Determination of Speech Discrimination

A theoretical statistical analysis, which takes into consideration the random effect in the determination of speech discrimination, demonstrates that binomial distribution can be used to assess the reliability of the result. A clinical study supports the theory, which shows that reliability depends on the discrimination of the patient, length of word list and upon the character of the word material. The standard deviation of the discrimination value at repeated measurements on the same patient is, in theory, proportionally inverse to the square root of the number of words in the list. Curves with confidence intervals for the discrimination values obtained are presented and also diagrams indicating when two different discrimination results deviate significantly from each other. Curtailment of a 50-word list to a 25-word list is recommended only in those cases where the patient has at maximum one mistake in these 25 words. In order that reliability can be estimated, the length of the word list used always s...