Speech recognition on mobile devices in noisy environments

2018-05-05
Yurtcan, Yaser
Günel Kılıç, Banu
The use of speech recognition on mobile devices has been possible with the development of cloud systems and has been used for about 10 years. However, in noisy environments, the problem of speech recognition with low error rate still persists. In this study, different speech samples have been recorded using a compact microphone array in noisy environments and a data set has been created by processing them with a real-time noise cancellation algorithm. Speech recognition performance has been tested on the generated dataset using Google cloud system. As a result of the test, speech recognition performance of the cloud systems according to the noise level was observed. Results show that in order to apply speech recognition using cloud computing systems on mobile devices, the noise level has to be low or real-time noise cancellation algorithms are needed.

Suggestions

Social Presence in Synchronous Text-Based Computer-Mediated Communication
AKAYOĞLU, SEDAT; ALTUN, ARİF; Stevens, Vance (2009-12-01)
Problem Statement: In recent years, the substantial technological development in various online environments has been used in educational environments. However, these online environments are still new for many teachers, researchers and students. Thus, researchers have attempted to determine the discourse patterns of these environments from different perspectives. Social presence is one of these dimensions; however, there has been little research on social presence in synchronous CMC environments. This study...
Wireless speech recognition using fixed point mixed excitation linear prediction (MELP) vocoder
Acar, D; Karci, MH; Ilk, HG; Demirekler, Mübeccel (2002-07-19)
A bit stream based front-end for wireless speech recognition system that operates on fixed point mixed excitation linear prediction (MELP) vocoder is presented in this paper. Speaker dependent, isolated word recognition accuracies obtained from conventional and bit stream based front-end systems are obtained and their statistical significance is discussed. Feature parameters are extracted from original (wireline) and decoded speech (conventional) and from the quantized spectral information (bit stream) of t...
SPEECH DETECTION ON BROADCAST AUDIO
Zubari, Unal; Ozan, Ezgi Can; Acar, Banu Oskay; Çiloğlu, Tolga; Esen, Ersin; Ates, Tugrul K.; Onur, Duygu Oskay (2010-08-27)
Speech boundary detection contributes to performance of speech based applications such as speech recognition and speaker recognition. Speech boundary detector implemented in this study works on broadcast audio as a pre-processor module of a keyword spotter. Speech boundary detection is handled in 3 steps. At first step, audio data is segmented into homogeneous regions in an unsupervised manner. After an ACTIVITY/NON-ACTIVITY decision is made for each region, ACTIVITY regions are classified as Speech/Non-spe...
Optimizing core signal processing functions on a superscalar SIMD architecture
Uslu, Çağrı; Bazlamaçcı, Cüneyt Fehmi; Department of Electrical and Electronics Engineering (2019)
Digital Signal Processing (DSP) is the basis of many technologies, such as Image Processing, Speech Recognition, Radars, etc. Use of electronic devices such as smart- phones, smartwatches, self-driving cars and autonomous robots that take advantage of these technologies becomes widespread and hence it is more critical than ever for these technologies to be realized with high efficiency on cheaper and less power- hungry devices. Cortex-A15 processor architecture is one of the solutions from ARM to this requi...
FlexRay protokolu statik bölütü için mesaj çizelgelenmesi
Schmidt, Ece Güran; Schmidt, Klaus Verner (2008-11-26)
Son yıllarda zamanlamanın kritik olduğu uygulamalar için veriyolu tabanlı araç içi haberleşme protokollari geliştirilmiştir. FlexRay protokolünun bu protokollar arasında fiili standard olması beklenmektedir. Bu makalede periyodik mesajların FlexRay statik bölüt’ünde (static segment) olan bant genişliğini en verimli kullanacak şekilde çizelgelenmesi problemi incelenmektedir. Bu amaçla uygun bir sistem mimarisi önerilmekte, basarım ölçütleri tanımlanmakta ve bir tamsayı doğrusal programlama problemi oluşturul...
Citation Formats
Y. Yurtcan and B. Günel Kılıç, “Speech recognition on mobile devices in noisy environments,” presented at the 26th IEEE Signal Processing and Communications Applications Conference (SIU), Izmir, TURKEY, 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/31218.