Influence of the speaking style and the noise spectral tilt on the lombard reflex and automatic speech recognition
نویسندگان
چکیده
To study the Lombard reflex, more realistic databases representing real world conditions need to be recorded and analyzed. In this paper we 1) propose a procedure to record Lombard data which provides a good approximation of realistic conditions and 2) present a comparison between two sets of experiments where subjects are in communication with a device while listening to noise through open-ear headphones and where subjects are reading a list. By studying acoustic correlates of the Lombard reflex and performing off-line speakerindependent recognition experiments it is shown that the communication factor affects the Lombard reflex. We also show evidence that several types of noise differing mainly by their spectral tilt induce different acoustic changes. This result reinforces the notion that it is difficult to separate the speaker from the environment stressor (in this case the noise) when studying the Lombard reflex.
منابع مشابه
Impact of the Unknown Communication Channel on Automatic Speech Recognition: A Review
This review article summarizes the main difficulties encountered in Automatic Speech Recognition (ASR) when the type of communication channel is not known. This problem is crucial for the development of successful applications in promising domains such as computer telephony and cars. The main technical problems encountered are due to the speaker and the task (e.g. speaking style, Lombard reflex...
متن کاملThe contribution of changes in F0 and spectral tilt to increased intelligibility of speech produced in noise
Talkers modify the way they speak in the presence of noise. As well as increases in voice level and fundamental frequency (F0), a flattening of spectral tilt is observed. The resulting ‘‘Lombard speech” is typically more intelligible than speech produced in quiet, even when level differences are removed. What is the cause of the enhanced intelligibility of Lombard speech? The current study expl...
متن کاملImproving the performance of MFCC for Persian robust speech recognition
The Mel Frequency cepstral coefficients are the most widely used feature in speech recognition but they are very sensitive to noise. In this paper to achieve a satisfactorily performance in Automatic Speech Recognition (ASR) applications we introduce a noise robust new set of MFCC vector estimated through following steps. First, spectral mean normalization is a pre-processing which applies to t...
متن کاملThe Lombard effect: a reflex to better communicate with others in noise
To study the Lombard reflex, more realistic databases representing real-world conditions need to be recorded and analyzed. In this paper we 1) summarize a procedure to record Lombard data which provides a good approximation of realistic conditions, 2) present an analysis per class of sounds for duration and energy of words recorded while subjects are listening to noise through open-ear headphon...
متن کاملLombard effect compensation and noise suppression for noisy Lombard speech recognition
The performance of speech recognition system degrades rapidly in the presence of ambient noise. To reduce the degradation, a degradation model is proposed which represents the spectral changes of speech signal uttered in noisy environments. The model uses frequency warping and amplitude scaling of each frequency band to simulate the variations of formant location, formant bandwidth, pitch, spec...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1998