The Influence of Lombard Effect on Speech Recognition

Vlaj, Damjan; Kačič, Zdravko

doi:10.5772/17520

Cited by 13 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fifth, users adapt their vocal features automatically to increase intelligibility in noisy environments, referred to as the Lombard effect. Vlaj & Kacic (2011) describe the influence of this effect on speech recognition. Marxer and colleagues (2018) discuss the speechin-noise problem, the Lombard Effect, and the need for speech recognition systems operating in a noisy environment to be trained on Lombard speech.…”

Section: Environmental Characteristicsmentioning

confidence: 99%

An Ergonomic Framework for Researching and Designing Speech Recognition Technologies in Health Care with an Emphasis on Safety

Arnold

Fuller

2019

Proceedings of the International Symposium on Human Factors and

View full text Add to dashboard Cite

Automatic speech recognition (ASR) systems and speech interfaces are becoming increasingly prevalent. This includes increases in and expansion of use of these technologies for supporting work in health care. Computer-based speech processing has been extensively studied and developed over decades. Speech processing tools have been fine-tuned through the work of Speech and Language Researchers. Researchers have previously and continue to describe speech processing errors in medicine. The discussion provided in this paper proposes an ergonomic framework for speech recognition to expand and further describe this view of speech processing in supporting clinical work. With this end in mind, we hope to build on previous work and emphasize the need for increased human factors involvement in this area while also facilitating the discussion of speech recognition in contexts that have been explored in the human factors domain. Human factors expertise can contribute through proactively describing and designing these critical interconnected socio-technical systems with error-tolerance in mind.

show abstract

Section: Environmental Characteristicsmentioning

confidence: 99%

An Ergonomic Framework for Researching and Designing Speech Recognition Technologies in Health Care with an Emphasis on Safety

Arnold

Fuller

2019

Proceedings of the International Symposium on Human Factors and

View full text Add to dashboard Cite

show abstract

“…The most common changes found in healthy, vocally untrained subjects describe adaptations of increasing the voice sound pressure level (SPL) and fundamental frequency (ƒ o ) [ 26 , 27 , 28 ] as well as additional effects on the acoustic properties of voice production, such as pronounced amplitude modulations [ 29 ] and increases in duration and intensity of vowel production [ 27 , 30 ]. In particular, changes in the duration of vowels and voiced consonants were found to be typical for Lombard speech [ 24 , 31 , 32 ]. Generally, lengthened vocalizations in noisy environments were found to be interrelated with the voice SPL, particularly on stressed words [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Vocal Behavior of Teachers Reading with Raised Voice in a Noisy Environment

Nusseck

Immerz

Richter

et al. 2022

IJERPH

View full text Add to dashboard Cite

(1) Objective: Teaching is a particularly voice-demanding occupation. Voice training provided during teachers’ education is often insufficient and thus teachers are at risk of developing voice disorders. Vocal demands during teaching are not only characterized by speaking for long durations but also by speaking in noisy environments. This provokes the so-called Lombard effect, which intuitively leads to an increase in voice intensity, pitch and phonation time in laboratory studies. However, this effect has not been thoroughly investigated in realistic teaching scenarios. (2) Methods: This study thus examined how 13 experienced, but vocally untrained, teachers behaved when reading in a noisy compared to quiet background environment. The quiet and noisy conditions were provided by a live audience either listening quietly or making noise by talking to each other. By using a portable voice accumulator, the fundamental frequency, sound pressure level of the voice and the noise as well as the phonation time were recorded in both conditions. (3) Results: The results showed that the teachers mainly responded according to the Lombard effect. In addition, analysis of phonation time revealed that they failed to increase inhalation time and appeared to lose articulation through the shortening of voiceless consonants in the noisy condition. (4) Conclusion: The teachers demonstrated vocally demanding behavior when speaking in the noisy condition, which can lead to vocal fatigue and cause dysphonia. The findings underline the necessity for specific voice training in teachers’ education, and the content of such training is discussed in light of the results.

show abstract

“…This experiment was not performed in the RW but was added to this work because of the importance of vowels in intelligibility (Kewley-Port et al, 2007) and the scarcity of literature on that aspect of the Lombard effect (Junqua, 1993;Vlaj, Kačič, 2011).…”

Section: Duration Of Vowelsmentioning

confidence: 99%

“…Most of the works were done in English, often based on closed speech corpora like numbers. Few works on the effect in other languages can be found: French, Czech and Slovenian (Garnier, 2010;Boril, Pollak, 2005;Vlaj, Kačič, 2011).…”

Section: Introductionmentioning

confidence: 99%

Lombard Effect in Polish Speech and its Comparison in English Speech

Kleczkowski¹,

Żak²,

Kr�l-Nowak³

2017

Archives of Acoustics

View full text Add to dashboard Cite

The first extensive investigation on the Lombard effect with Polish speech has been performed. Characteristic parameters of Lombard speech were measured: intensity, fundamental frequency, spectral tilt, duration of words, duration of pauses and duration of vowels. The effect was investigated in a task involving real communication -solving a Sudoku puzzle. The speakers produced speech in quiet and in three different backgrounds: competing speech, speech-shaped noise and speech-modulated noise. The experimental conditions were held as close as possible to those in the study by Cooke and Lu (2010) so that conclusions could be drawn whether differences between the Lombard effect in Polish speech and English speech existed. Most of the findings on the Lombard effect known from the literature have been confirmed with Polish speech. In three parameters, Polish speakers were more sensitive to modulated backgrounds while English speakers were more sensitive to a stationary background. In both languages, the modulated backgrounds induced speakers to extend pauses in the communication tasks.

show abstract

The Influence of Lombard Effect on Speech Recognition

Cited by 13 publications

References 14 publications

An Ergonomic Framework for Researching and Designing Speech Recognition Technologies in Health Care with an Emphasis on Safety

An Ergonomic Framework for Researching and Designing Speech Recognition Technologies in Health Care with an Emphasis on Safety

Vocal Behavior of Teachers Reading with Raised Voice in a Noisy Environment

Lombard Effect in Polish Speech and its Comparison in English Speech

Contact Info

Product

Resources

About